Showing 1–50 of 227 results for author: Skoglund, M

Addressing Limited Data in Auditory Attention Decoding with Diffusion Generative Models

Authors: David Rannaleet, Victor Gunnarsson, Bo Bernhardsson, Martin A. Skoglund, Emina Alickovic

Abstract: Limited training data constrains deep learning models for Auditory Attention Decoding (AAD) in hearing aids (HAs). AAD uses electroencephalogram (EEG) data to decode listener's attention, enabling real-time tracking of specific sound sources. However, achieving high AAD performance with short time windows typical in HAs (<=1s) is challenging due to the scarcity of real-world speech-evoked EEG data… ▽ More Limited training data constrains deep learning models for Auditory Attention Decoding (AAD) in hearing aids (HAs). AAD uses electroencephalogram (EEG) data to decode listener's attention, enabling real-time tracking of specific sound sources. However, achieving high AAD performance with short time windows typical in HAs (<=1s) is challenging due to the scarcity of real-world speech-evoked EEG data. To address this issue, we investigate diffusion probabilistic models (DPMs) for generating synthetic speech-evoked EEG data. DPMs learn the underlying complex data structure through a denoising process and can generate realistic samples suitable for data augmentation. We evaluate the use of synthetic EEG data for augmenting datasets in locus-of-attention (LoA) classification tasks. Our experiments demonstrate that DPMs can generate realistic EEG signals and that incorporating synthetic data significantly improves AAD performance compared to models trained solely on measured EEG data (p<0.05). These results highlight the potential of diffusion-based data augmentation to mitigate training data limitations and improve the robustness of short-window AAD models in HA applications. △ Less

Submitted 20 July, 2026; originally announced July 2026.

Minimax Quantile Lower Bounds for Interactive Statistical Decision Making with Privacy

Authors: Raghav Bongole, Amirreza Zamani, Tobias J. Oechtering, Mikael Skoglund

Abstract: Minimax risk and regret are expectation-based criteria and do not capture rare but consequential failures. To address this concern, we develop a $δ$-explicit minimax-quantile theory for interactive statistical decision making (ISDM). We first provide structural relations between minimax quantiles, lower minimax quantiles, and minimax risk. This includes a quantile-to-expectation conversion and an… ▽ More Minimax risk and regret are expectation-based criteria and do not capture rare but consequential failures. To address this concern, we develop a $δ$-explicit minimax-quantile theory for interactive statistical decision making (ISDM). We first provide structural relations between minimax quantiles, lower minimax quantiles, and minimax risk. This includes a quantile-to-expectation conversion and an equivalence between strict and lower minimax quantiles outside a countable set of confidence levels. We then derive two converse tools for ISDM: a high-probability interactive Fano's method and a high-probability interactive Le Cam's method. Then, we show that mutual-information (MI) privacy can be handled in the same framework by restricting the admissible decision class. For coordinatewise Gaussian privatization, we derive a two-point template that isolates the privacy-induced variance inflation. We instantiate this template for Gaussian mean estimation, and use the same two-point strategy directly for two-armed Gaussian bandits. We then derive a minimax quantile lower bound for the $K$-armed Gaussian bandit problem, showing that the interactive Fano method captures the exploration cost over multiple possible best arms. The resulting lower bounds are explicit in the confidence level $δ$ and in the privacy budget for the private problems. They yield $\log(1/δ)/n$ scaling for squared-error Gaussian mean estimation, $\sqrt{T\log(1/δ)}$ scaling for two-armed bounded-mean Gaussian bandits, and $\sqrt{KT\log(1/δ)}$-type scaling for the $K$-armed bandits, with privacy appearing through a Gaussian variance-inflation factor for the private problems. △ Less

Submitted 22 June, 2026; originally announced June 2026.

Sparse Discrete Laplace and Gaussian Mechanisms under Local Differential Privacy

Authors: Amirreza Zamani, Sajad Daei, Parastoo Sadeghi, Mikael Skoglund

Abstract: We study sparse locally private channels of the form $M(y\mid x)\propto w(x,y) 1\{y\in S(x)\},$ where the admissible output set $S(x)$ is allowed to depend on the private input $x$ and is assumed to be small. Here, we consider the sparse discrete-Laplace family with kernel $w(x,y)=e^{-λd(x,y)}$ and the sparse Gaussian family with kernel $w(x,y)=e^{-d(x,y)^2/(2σ^2)}$. For both families we give exac… ▽ More We study sparse locally private channels of the form $M(y\mid x)\propto w(x,y) 1\{y\in S(x)\},$ where the admissible output set $S(x)$ is allowed to depend on the private input $x$ and is assumed to be small. Here, we consider the sparse discrete-Laplace family with kernel $w(x,y)=e^{-λd(x,y)}$ and the sparse Gaussian family with kernel $w(x,y)=e^{-d(x,y)^2/(2σ^2)}$. For both families we give exact characterizations of pure and approximate local differential privacy. For pure $\varepsilon$-local differential privacy, we show that input-dependent sparse supports are obtained when all supports coincide. For $(\varepsilon,δ)$-local differential privacy, we derive exact formulas for the privacy defect in terms of support leakage and excess privacy loss on the overlap region. We then specialize the analysis to radius-truncated sparse discrete-Laplace and radius-truncated sparse Gaussian mechanisms and obtain explicit privacy-sparsity tradeoffs in terms of the support size $s$. In particular, we show that nontrivial approximate local privacy requires a minimum support size, whereas larger supports reduce support leakage but increase distortion. For the Gaussian family, the overlap term exhibits an additional quadratic dependence on the support radius, which implies a sharper tradeoff between privacy and sparsity. These results identify the support cardinality as the intrinsic complexity parameter of the mechanism and yield an optimal design principle: choose the smallest support size that satisfies the target privacy constraint. △ Less

Submitted 10 May, 2026; originally announced May 2026.

Zero-determinant Strategy for Moving Target Defense: Existence, Performance, and Computation

Authors: Zhaoyang Cheng, Guanpu Chen, Yiguang Hong, Ming Cao, Mikael Skoglund

Abstract: Moving Target Defense (MTD) is commonly formulated as a repeated security game to mitigate persistent threats. Although the strong Stackelberg equilibrium (SSE) characterizes the defender's optimal strategy in the leader-follower framework, computing the SSE often incurs high computational complexity, which significantly limits its practical deployment in MTD problems with multiple targets. This p… ▽ More Moving Target Defense (MTD) is commonly formulated as a repeated security game to mitigate persistent threats. Although the strong Stackelberg equilibrium (SSE) characterizes the defender's optimal strategy in the leader-follower framework, computing the SSE often incurs high computational complexity, which significantly limits its practical deployment in MTD problems with multiple targets. This paper proposes adopting a zero-determinant (ZD) strategy for constructing an MTD strategy that achieves both high defensive performance and substantially low computational complexity. We first derive a necessary and sufficient condition for the existence of ZD strategies and investigate the performance of ZD strategies, which shows their upper-bound performance matches that of the SSE strategy. We then formulate two programs to find the optimal ZD strategy parameters under different conditions. Moreover, we design an algorithm to compute the proposed ZD strategies, along with the computational complexity analysis in comparison with the traditional SSE computation. Finally, we conduct experiments on two practical applications to verify our results. △ Less

Submitted 8 May, 2026; originally announced May 2026.

A Hierarchical Sampling Framework for bounding the Generalization Error of Federated Learning

Authors: Dario Filatrella, Ragnar Thobaben, Mikael Skoglund

Abstract: We study expected generalization bounds for the Hierarchical Federated Learning (HFL) setup using Wasserstein distance. We introduce a generalized framework in which data is sampled hierarchically, and we model it with a multi-layered tree structure that induces dependencies among the clients' datasets. We derive generalization bounds in terms of Wasserstein distance under the Lipschitz assumption… ▽ More We study expected generalization bounds for the Hierarchical Federated Learning (HFL) setup using Wasserstein distance. We introduce a generalized framework in which data is sampled hierarchically, and we model it with a multi-layered tree structure that induces dependencies among the clients' datasets. We derive generalization bounds in terms of Wasserstein distance under the Lipschitz assumption on the loss function, by applying a supersample construction that allows us to measure the sensitivity of the algorithm to the change of a single node in the sampling tree. By leveraging the FL structure, we recover and strictly imply existing state-of-the-art conditional mutual information (CMI) bounds in the case of bounded losses. We also show that our bound can be applied together with Differential Privacy assumptions, to recover generalization bounds based on algorithmic privacy. To assess the tightness of our bounds, we study the Gaussian Location Model (GLM) and show that we recover the actual asymptotic rate of the generalization error. △ Less

Submitted 5 May, 2026; originally announced May 2026.

Channel-coded Over-the-Air Computation

Authors: Shudi Weng, Ming Xiao, Mikael Skoglund

Abstract: This letter studies channel coding for over-the-air computation (AirComp). AirComp enables efficient wireless data aggregation, where computation accuracy is the key performance metric. However, this accuracy is sensitive to channel impairments. As a promising solution, the role of channel coding in AirComp has been largely unexplored, creating a critical gap in achieving reliable AirComp systems.… ▽ More This letter studies channel coding for over-the-air computation (AirComp). AirComp enables efficient wireless data aggregation, where computation accuracy is the key performance metric. However, this accuracy is sensitive to channel impairments. As a promising solution, the role of channel coding in AirComp has been largely unexplored, creating a critical gap in achieving reliable AirComp systems. To address this, we propose a novel channel coding scheme tailored for AirComp that preserves the aggregation structure while mitigating channel distortions. We show that the computation error decreases with the coding rate and can asymptotically approach zero. Both theoretical and simulation results demonstrate that the proposed scheme significantly enhances computation performance. △ Less

Submitted 3 May, 2026; originally announced May 2026.

Perfectly Private Over-the-Air Computation

Authors: Shudi Weng, Ming Xiao, Mikael Skoglund

Abstract: This paper studies a key research question: how to achieve perfect privacy in over-the-air computation (AirComp)? The problem is particularly intriguing due to a dilemma. Real-field operations can ensure invertibility but generally introduce statistical dependence, resulting in inevitable privacy leakage. In contrast, modulo operations can decorrelate the output from the original message, but suff… ▽ More This paper studies a key research question: how to achieve perfect privacy in over-the-air computation (AirComp)? The problem is particularly intriguing due to a dilemma. Real-field operations can ensure invertibility but generally introduce statistical dependence, resulting in inevitable privacy leakage. In contrast, modulo operations can decorrelate the output from the original message, but suffer from the ill-posed invertibility when applied over non-prime groups (e.g., the real field). This raises a subtle yet fundamental question: Does perfect privacy intrinsically conflict with AirComp? We show that the answer is no. By carefully leveraging the interplay between real-field and modulo operations, perfect privacy and accurate computation can, in fact, be achieved simultaneously, enabling perfectly private aggregation. △ Less

Submitted 30 April, 2026; originally announced April 2026.

Instantiating Bayesian CVaR lower bounds in Interactive Decision Making Problems

Authors: Raghav Bongole, Tobias J. Oechtering, Mikael Skoglund

Abstract: Recent work established a generalized-Fano framework for lower bounding prior-predictive (Bayesian) CVaR in interactive statistical decision making. In this paper, we show how to instantiate that framework in concrete interactive problems and derive explicit Bayesian CVaR lower bounds from its abstract corollaries. Our approach compares a hard model with a reference model using squared Hellinger d… ▽ More Recent work established a generalized-Fano framework for lower bounding prior-predictive (Bayesian) CVaR in interactive statistical decision making. In this paper, we show how to instantiate that framework in concrete interactive problems and derive explicit Bayesian CVaR lower bounds from its abstract corollaries. Our approach compares a hard model with a reference model using squared Hellinger distance, and combines a lower bound on a reference hinge term with a bound on the distinguishability of the two models. We apply this approach to canonical examples, including Gaussian bandits, and obtain explicit bounds that make the dependence on key problem parameters transparent. These results show how the generalized-Fano Bayesian CVaR framework can be used as a practical lower-bound tool for interactive learning and risk-sensitive decision making. △ Less

Submitted 14 April, 2026; originally announced April 2026.

Byzantine-Robust and Communication-Efficient Distributed Training: Compressive and Cyclic Gradient Coding

Authors: Chengxi Li, Youssef Allouah, Rachid Guerraoui, Mikael Skoglund, Ming Xiao

Abstract: In this paper, we study the problem of distributed training (DT) under Byzantine attacks with communication constraints. While prior work has developed various robust aggregation rules at the server to enhance robustness to Byzantine attacks, the existing methods suffer from a critical limitation in that the solution error does not diminish when the local gradients sent by different devices vary c… ▽ More In this paper, we study the problem of distributed training (DT) under Byzantine attacks with communication constraints. While prior work has developed various robust aggregation rules at the server to enhance robustness to Byzantine attacks, the existing methods suffer from a critical limitation in that the solution error does not diminish when the local gradients sent by different devices vary considerably, as a result of data heterogeneity among the subsets held by different devices. To overcome this limitation, we propose a novel DT method, cyclic gradient coding-based DT (LAD). In LAD, the server allocates the entire training dataset to the devices before training begins. In each iteration, it assigns computational tasks redundantly to the devices using cyclic gradient coding. Each honest device then computes local gradients on a fixed number of data subsets and encodes the local gradients before transmitting to the server. The server aggregates the coded vectors from the honest devices and the potentially incorrect messages from Byzantine devices using a robust aggregation rule. Leveraging the redundancy of computation across devices, the convergence performance of LAD is analytically characterized, demonstrating improved robustness against Byzantine attacks and significantly lower solution error. Furthermore, we extend LAD to a communication-efficient variant, compressive and cyclic gradient coding-based DT (Com-LAD), which further reduces communication overhead under constrained settings. Numerical results validate the effectiveness of the proposed methods in enhancing both Byzantine resilience and communication efficiency. △ Less

Submitted 17 March, 2026; originally announced March 2026.

Biased Compression in Gradient Coding for Distributed Learning

Authors: Chengxi Li, Ming Xiao, Mikael Skoglund

Abstract: Communication bottlenecks and the presence of stragglers pose significant challenges in distributed learning (DL). To deal with these challenges, recent advances leverage unbiased compression functions and gradient coding. However, the significant benefits of biased compression remain largely unexplored. To close this gap, we propose Compressed Gradient Coding with Error Feedback (COCO-EF), a nove… ▽ More Communication bottlenecks and the presence of stragglers pose significant challenges in distributed learning (DL). To deal with these challenges, recent advances leverage unbiased compression functions and gradient coding. However, the significant benefits of biased compression remain largely unexplored. To close this gap, we propose Compressed Gradient Coding with Error Feedback (COCO-EF), a novel DL method that combines gradient coding with biased compression to mitigate straggler effects and reduce communication costs. In each iteration, non-straggler devices encode local gradients from redundantly allocated training data, incorporate prior compression errors, and compress the results using biased compression functions before transmission. The server aggregates these compressed messages from the non-stragglers to approximate the global gradient for model updates. We provide rigorous theoretical convergence guarantees for COCO-EF and validate its superior learning performance over baseline methods through empirical evaluations. As far as we know, we are among the first to rigorously demonstrate that biased compression has substantial benefits in DL, when gradient coding is employed to cope with stragglers. △ Less

Submitted 17 March, 2026; originally announced March 2026.

Convexity Meets Curvature: Lifted Near-Field Super-Resolution

Authors: Sajad Daei, Gábor Fodor, Mikael Skoglund

Abstract: Extra-large apertures, high carrier frequencies, and integrated sensing and communications (ISAC) are pushing array processing into the Fresnel region, where spherical wavefronts induce a range-dependent phase across the aperture. This curvature breaks the Fourier/Vandermonde structure behind classical subspace methods, and it is especially limiting with hybrid front-ends that provide only a small… ▽ More Extra-large apertures, high carrier frequencies, and integrated sensing and communications (ISAC) are pushing array processing into the Fresnel region, where spherical wavefronts induce a range-dependent phase across the aperture. This curvature breaks the Fourier/Vandermonde structure behind classical subspace methods, and it is especially limiting with hybrid front-ends that provide only a small number of pilot measurements. Consequently, practical systems need continuous angle resolution and joint angle-range inference where many near-field approaches still rely on costly 2D gridding. We show that convexity can meet curvature via a lifted, gridless superresolution framework for near-field measurements. The key is a Bessel-Vandermonde factorization of the Fresnel-phase manifold that exposes a hidden Vandermonde structure in angle while isolating the range dependence into a compact coefficient map. Building on this, we introduce a lifting that maps each range bin and continuous angle to a structured rank-one atom, converting the nonlinear near-field model into a linear inverse problem over a row-sparse matrix. Recovery is posed as atomic-norm minimization and an explicit dual characterization via bounded trigonometric polynomials yields certificate-based localization that super-resolves off-grid angles and identifies active range bins. Simulations with strongly undersampled hybrid observations validate reliable joint angle-range recovery for next-generation wireless and ISAC systems. △ Less

Submitted 15 February, 2026; originally announced February 2026.

Quantization-Aware Collaborative Inference for Large Embodied AI Models

Authors: Zhonghao Lyu, Ming Xiao, Mikael Skoglund, Merouane Debbah, H. Vincent Poor

Abstract: Large artificial intelligence models (LAIMs) are increasingly regarded as a core intelligence engine for embodied AI applications. However, the massive parameter scale and computational demands of LAIMs pose significant challenges for resource-limited embodied agents. To address this issue, we investigate quantization-aware collaborative inference (co-inference) for embodied AI systems. First, we… ▽ More Large artificial intelligence models (LAIMs) are increasingly regarded as a core intelligence engine for embodied AI applications. However, the massive parameter scale and computational demands of LAIMs pose significant challenges for resource-limited embodied agents. To address this issue, we investigate quantization-aware collaborative inference (co-inference) for embodied AI systems. First, we develop a tractable approximation for quantization-induced inference distortion. Based on this approximation, we derive lower and upper bounds on the quantization rate-inference distortion function, characterizing its dependence on LAIM statistics, including the quantization bit-width. Next, we formulate a joint quantization bit-width and computation frequency design problem under delay and energy constraints, aiming to minimize the distortion upper bound while ensuring tightness through the corresponding lower bound. Extensive evaluations validate the proposed distortion approximation, the derived rate-distortion bounds, and the effectiveness of the proposed joint design. Particularly, simulations and real-world testbed experiments demonstrate the effectiveness of the proposed joint design in balancing inference quality, latency, and energy consumption in edge embodied AI systems. △ Less

Submitted 13 February, 2026; originally announced February 2026.

Coding-Enforced Resilient and Secure Aggregation for Hierarchical Federated Learning

Authors: Shudi Weng, Ming Xiao, Mikael Skoglund

Abstract: Hierarchical federated learning (HFL) has emerged as an effective paradigm to enhance link quality between clients and the server. However, ensuring model accuracy while preserving privacy under unreliable communication remains a key challenge in HFL, as the coordination among privacy noise can be randomly disrupted. To address this limitation, we propose a robust hierarchical secure aggregation s… ▽ More Hierarchical federated learning (HFL) has emerged as an effective paradigm to enhance link quality between clients and the server. However, ensuring model accuracy while preserving privacy under unreliable communication remains a key challenge in HFL, as the coordination among privacy noise can be randomly disrupted. To address this limitation, we propose a robust hierarchical secure aggregation scheme, termed H-SecCoGC, which integrates coding strategies to enforce structured aggregation. The proposed scheme not only ensures accurate global model construction under varying levels of privacy, but also avoids the partial participation issue, thereby significantly improving robustness, privacy preservation, and learning efficiency. Both theoretical analyses and experimental results demonstrate the superiority of our scheme under unreliable communication across arbitrarily strong privacy guarantees △ Less

Submitted 25 January, 2026; originally announced January 2026.

Neural Tracking of Sustained Attention, Attention Switching, and Natural Conversation in Audiovisual Environments using Mobile EEG

Authors: Johanna Wilroth, Oskar Keding, Martin A. Skoglund, Maria Sandsten, Martin Enqvist, Emina Alickovic

Abstract: Everyday communication is dynamic and multisensory, often involving shifting attention, overlapping speech and visual cues. Yet, most neural attention tracking studies are still limited to highly controlled lab settings, using clean, often audio-only stimuli and requiring sustained attention to a single talker. This work addresses that gap by introducing a novel dataset from 24 normal-hearing part… ▽ More Everyday communication is dynamic and multisensory, often involving shifting attention, overlapping speech and visual cues. Yet, most neural attention tracking studies are still limited to highly controlled lab settings, using clean, often audio-only stimuli and requiring sustained attention to a single talker. This work addresses that gap by introducing a novel dataset from 24 normal-hearing participants. We used a mobile electroencephalography (EEG) system (44 scalp electrodes and 20 cEEGrid electrodes) in an audiovisual (AV) paradigm with three conditions: sustained attention to a single talker in a two-talker environment, attention switching between two talkers, and unscripted two-talker conversations with a competing single talker. Analysis included temporal response functions (TRFs) modeling, optimal lag analysis, selective attention classification with decision windows ranging from 1.1s to 35s, and comparisons of TRFs for attention to AV conversations versus side audio-only talkers. Key findings show significant differences in the attention-related P2-peak between attended and ignored speech across conditions for scalp EEG. No significant change in performance between switching and sustained attention suggests robustness for attention switches. Optimal lag analysis revealed narrower peak for conversation compared to single-talker AV stimuli, reflecting the additional complexity of multi-talker processing. Classification of selective attention was consistently above chance (55-70% accuracy) for scalp EEG, while cEEGrid data yielded lower correlations, highlighting the need for further methodological improvements. These results demonstrate that mobile EEG can reliably track selective attention in dynamic, multisensory listening scenarios and provide guidance for designing future AV paradigms and real-world attention tracking applications. △ Less

Submitted 21 January, 2026; originally announced January 2026.

Comments: Submitted to European Journal of Neuroscience

On Resilient and Efficient Linear Secure Aggregation in Hierarchical Federated Learning

Authors: Shudi Weng, Xiang Zhang, Yizhou Zhao, Giuseppe Caire, Ming Xiao, Mikael Skoglund

Abstract: In this paper, we study the fundamental limits of hierarchical secure aggregation under unreliable communication. We consider a hierarchical network where each client connects to multiple relays, and both client-to-relay and relay-to-server links are intermittent. Under this setting, we characterize the minimum communication and randomness costs required to achieve robust secure aggregation. We th… ▽ More In this paper, we study the fundamental limits of hierarchical secure aggregation under unreliable communication. We consider a hierarchical network where each client connects to multiple relays, and both client-to-relay and relay-to-server links are intermittent. Under this setting, we characterize the minimum communication and randomness costs required to achieve robust secure aggregation. We then propose an optimal protocol that attains these minimum costs, and establish its optimality through a matching converse proof. In addition, we introduce an improved problem formulation that bridges the gap between existing information-theoretic secure aggregation protocols and practical real-world federated learning problems. △ Less

Submitted 19 January, 2026; originally announced January 2026.

Generalizing the Fano inequality further

Authors: Raghav Bongole, Tobias J. Oechtering, Mikael Skoglund

Abstract: Interactive statistical decision making (ISDM) features algorithm-dependent data generated through interaction. Existing information-theoretic lower bounds in ISDM largely target expected risk, while tail-sensitive objectives are less developed. We generalize the interactive Fano framework of Chen et al. by replacing the hard success event with a randomized one-bit statistic representing an arbitr… ▽ More Interactive statistical decision making (ISDM) features algorithm-dependent data generated through interaction. Existing information-theoretic lower bounds in ISDM largely target expected risk, while tail-sensitive objectives are less developed. We generalize the interactive Fano framework of Chen et al. by replacing the hard success event with a randomized one-bit statistic representing an arbitrary bounded transform of the loss. This yields a Bernoulli f-divergence inequality, which we invert to obtain a two-sided interval for the transform, recovering the previous result as a special case. Instantiating the transform with a bounded hinge and using the Rockafellar-Uryasev representation, we derive lower bounds on the prior-predictive (Bayesian) CVaR of bounded losses. For KL divergence with the mixture reference distribution, the bound becomes explicit in terms of mutual information via Pinsker's inequality. △ Less

Submitted 17 January, 2026; originally announced January 2026.

Dobrushin Coefficients of Private Mechanisms Beyond Local Differential Privacy

Authors: Leonhard Grosse, Sara Saeidian, Tobias J. Oechtering, Mikael Skoglund

Abstract: We investigate Dobrushin coefficients of discrete Markov kernels that have bounded pointwise maximal leakage (PML) with respect to all distributions with a minimum probability mass bounded away from zero by a constant $c>0$. This definition recovers local differential privacy (LDP) for $c\to 0$. We derive achievable bounds on contraction in terms of a kernels PML guarantees, and provide mechanism… ▽ More We investigate Dobrushin coefficients of discrete Markov kernels that have bounded pointwise maximal leakage (PML) with respect to all distributions with a minimum probability mass bounded away from zero by a constant $c>0$. This definition recovers local differential privacy (LDP) for $c\to 0$. We derive achievable bounds on contraction in terms of a kernels PML guarantees, and provide mechanism constructions that achieve the presented bounds. Further, we extend the results to general $f$-divergences by an application of Binette's inequality. Our analysis yields tighter bounds for mechanisms satisfying LDP and extends beyond the LDP regime to any discrete kernel. △ Less

Submitted 2 July, 2026; v1 submitted 14 January, 2026; originally announced January 2026.

Comments: presented at ISIT 2026; full version including appendices

Sparse Point-wise Privacy Leakage: Mechanism Design and Fundamental Limits

Authors: Amirreza Zamani, Sajad Daei, Parastoo Sadeghi, Mikael Skoglund

Abstract: We study an information-theoretic privacy mechanism design problem, where an agent observes useful data $Y$ that is arbitrarily correlated with sensitive data $X$, and design disclosed data $U$ generated from $Y$ (the agent has no direct access to $X$). We introduce \emph{sparse point-wise privacy leakage}, a worst-case privacy criterion that enforces two simultaneous constraints for every disclos… ▽ More We study an information-theoretic privacy mechanism design problem, where an agent observes useful data $Y$ that is arbitrarily correlated with sensitive data $X$, and design disclosed data $U$ generated from $Y$ (the agent has no direct access to $X$). We introduce \emph{sparse point-wise privacy leakage}, a worst-case privacy criterion that enforces two simultaneous constraints for every disclosed symbol $u\in\mathcal{U}$: (i) $u$ may be correlated with at most $N$ realizations of $X$, and (ii) the total leakage toward those realizations is bounded. In the high-privacy regime, we use concepts from information geometry to obtain a local quadratic approximation of mutual information which measures utility between $U$ and $Y$. When the leakage matrix $P_{X|Y}$ is invertible, this approximation reduces the design problem to a sparse quadratic maximization, known as the Rayleigh-quotient problem, with an $\ell_0$ constraint. We further show that, for the approximated problem, one can without loss of optimality restrict attention to a binary released variable $U$ with a uniform distribution. For small alphabet sizes, the exact sparsity-constrained optimum can be computed via combinatorial support enumeration, which quickly becomes intractable as the dimension grows. For general dimensions, the resulting sparse Rayleigh-quotient maximization is NP-hard and closely related to sparse principal component analysis (PCA). We propose a convex semidefinite programming (SDP) relaxation that is solvable in polynomial time and provides a tractable surrogate for the NP-hard design, together with a simple rounding procedure to recover a feasible leakage direction. We also identify a sparsity threshold beyond which the sparse optimum saturates at the unconstrained spectral value and the SDP relaxation becomes tight. △ Less

Submitted 12 January, 2026; originally announced January 2026.

Land-then-transport: A Flow Matching-Based Generative Decoder for Wireless Image Transmission

Authors: Jingwen Fu, Ming Xiao, Mikael Skoglund, Dong In Kim

Abstract: Due to strict rate and reliability demands, wireless image transmission remains difficult for both classical layered designs and joint source-channel coding (JSCC), especially under low latency. Diffusion-based generative decoders can deliver strong perceptual quality by leveraging learned image priors, but iterative stochastic denoising leads to high decoding delay. To enable low-latency decoding… ▽ More Due to strict rate and reliability demands, wireless image transmission remains difficult for both classical layered designs and joint source-channel coding (JSCC), especially under low latency. Diffusion-based generative decoders can deliver strong perceptual quality by leveraging learned image priors, but iterative stochastic denoising leads to high decoding delay. To enable low-latency decoding, we propose a flow-matching (FM) generative decoder under a new land-then-transport (LTT) paradigm that tightly integrates the physical wireless channel into a continuous-time probability flow. For AWGN channels, we build a Gaussian smoothing path whose noise schedule indexes effective noise levels, and derive a closed-form teacher velocity field along this path. A neural-network student vector field is trained by conditional flow matching, yielding a deterministic, channel-aware ODE decoder with complexity linear in the number of ODE steps. At inference, it only needs an estimate of the effective noise variance to set the ODE starting time. We further show that Rayleigh fading and MIMO channels can be mapped, via linear MMSE equalization and singular-value-domain processing, to AWGN-equivalent channels with calibrated starting times. Therefore, the same probability path and trained velocity field can be reused for Rayleigh and MIMO without retraining. Experiments on MNIST, Fashion-MNIST, and DIV2K over AWGN, Rayleigh, and MIMO demonstrate consistent gains over JPEG2000+LDPC, DeepJSCC, and diffusion-based baselines, while achieving good perceptual quality with only a few ODE steps. Overall, LTT provides a deterministic, physically interpretable, and computation-efficient framework for generative wireless image decoding across diverse channels. △ Less

Submitted 12 January, 2026; originally announced January 2026.

Privacy-Utility Trade-offs Under Multi-Level Point-Wise Leakage Constraints

Authors: Amirreza Zamani, Parastoo Sadeghi, Mikael Skoglund

Abstract: An information-theoretic privacy mechanism design is studied, where an agent observes useful data $Y$ which is correlated with the private data $X$. The agent wants to reveal the information to a user, hence, the agent utilizes a privacy mechanism to produce disclosed data $U$ that can be revealed. We assume that the agent has no direct access to $X$, i.e., the private data is hidden. We study pri… ▽ More An information-theoretic privacy mechanism design is studied, where an agent observes useful data $Y$ which is correlated with the private data $X$. The agent wants to reveal the information to a user, hence, the agent utilizes a privacy mechanism to produce disclosed data $U$ that can be revealed. We assume that the agent has no direct access to $X$, i.e., the private data is hidden. We study privacy mechanism design that maximizes the disclosed information about $Y$, measured by the mutual information between $Y$ and $U$, while satisfying a point-wise constraint with different privacy leakage budgets. We introduce a new measure, called the \emph{multi-level point-wise leakage}, which allows us to impose different leakage levels for different realizations of $U$. In contrast to previous studies on point-wise measures, which use the same leakage level for each realization, we consider a more general scenario in which each data point can leak information up to a different threshold. As a result, this concept also covers cases in which some data points should not leak any information about the private data, i.e., they must satisfy perfect privacy. In other words, a combination of perfect privacy and non-zero leakage can be considered. When the leakage is sufficiently small, concepts from information geometry allow us to locally approximate the mutual information. We show that when the leakage matrix $P_{X|Y}$ is invertible, utilizing this approximation leads to a quadratic optimization problem that has closed-form solution under some constraints. In particular, we show that it is sufficient to consider only binary $U$ to attain the optimal utility. This leads to simple privacy designs with low complexity which are based on finding the maximum singular value and singular vector of a matrix. △ Less

Submitted 8 January, 2026; originally announced January 2026.

An Information Geometric Approach to Fairness With Equalized Odds Constraint

Authors: Amirreza Zamani, Ayfer Özgür, Mikael Skoglund

Abstract: We study the statistical design of a fair mechanism that attains equalized odds, where an agent uses some useful data (database) $X$ to solve a task $T$. Since both $X$ and $T$ are correlated with some latent sensitive attribute $S$, the agent designs a representation $Y$ that satisfies an equalized odds, that is, such that $I(Y;S|T) =0$. In contrast to our previous work, we assume here that the a… ▽ More We study the statistical design of a fair mechanism that attains equalized odds, where an agent uses some useful data (database) $X$ to solve a task $T$. Since both $X$ and $T$ are correlated with some latent sensitive attribute $S$, the agent designs a representation $Y$ that satisfies an equalized odds, that is, such that $I(Y;S|T) =0$. In contrast to our previous work, we assume here that the agent has no direct access to $S$ and $T$; hence, the Markov chains $S - X - Y$ and $T - X - Y$ hold. Furthermore, we impose a geometric structure on the conditional distribution $P_{S|Y}$, allowing $Y$ and $S$ to have a small correlation, bounded by a threshold. When the threshold is small, concepts from information geometry allow us to approximate mutual information and reformulate the fair mechanism design problem as a quadratic program with closed-form solutions under certain constraints. For other cases, we derive simple, low-complexity lower bounds based on the maximum singular value and vector of a matrix. Finally, we compare our designs with the optimal solution in a numerical example. △ Less

Submitted 28 November, 2025; originally announced December 2025.

On Information Theoretic Fairness With A Bounded Point-Wise Statistical Parity Constraint: An Information Geometric Approach

Authors: Amirreza Zamani, Ayfer Özgür, Mikael Skoglund

Abstract: In this paper, we study an information-theoretic problem of designing a fair representation under a bounded point-wise statistical (demographic) parity constraint. More specifically, an agent uses some useful data (database) $X$ to solve a task $T$. Since both $X$ and $T$ are correlated with some latent sensitive attribute or secret $S$, the agent designs a representation $Y$ that satisfies a boun… ▽ More In this paper, we study an information-theoretic problem of designing a fair representation under a bounded point-wise statistical (demographic) parity constraint. More specifically, an agent uses some useful data (database) $X$ to solve a task $T$. Since both $X$ and $T$ are correlated with some latent sensitive attribute or secret $S$, the agent designs a representation $Y$ that satisfies a bounded point-wise statistical parity, that is, such that for all realizations of the representation $y\in\cal Y$, we have $χ^2(P_{S|y};P_S)\leq ε$. In contrast to our previous work, here we use the point-wise measure instead of a bounded mutual information, and we assume that the agent has no direct access to $S$ and $T$; hence, the Markov chains $S - X - Y$ and $T - X - Y$ hold. In this work, we design $Y$ that maximizes the mutual information $I(Y;T)$ about the task while satisfying a bounded compression rate constraint, that is, ensuring that $I(Y;X) \leq r$. Finally, $Y$ satisfies the point-wise bounded statistical parity constraint $χ^2(P_{S|y};P_S)\leq ε$. When $ε$ is small, concepts from information geometry allow us to locally approximate the KL-divergence and mutual information. To design the representation $Y$, we utilize this approximation and show that the main complex fairness design problem can be rewritten as a quadratic optimization problem that has simple closed-form solution under certain constraints. For the cases where the closed-form solution is not obtained we obtain lower bounds with low computational complexity. Here, we provide simple fairness designs with low complexity which are based on finding the maximum singular value and singular vector of a matrix. Finally, in a numerical example we compare our obtained results with the optimal solution. △ Less

Submitted 27 November, 2025; originally announced November 2025.

Robust Multi-modal Task-oriented Communications with Redundancy-aware Representations

Authors: Jingwen Fu, Ming Xiao, Zhonghao Lyu, Mikael Skoglund, Celimuge Wu

Abstract: Semantic communications for multi-modal data can transmit task-relevant information efficiently over noisy and bandwidth-limited channels. However, a key challenge is to simultaneously compress inter-modal redundancy and improve semantic reliability under channel distortion. To address the challenge, we propose a robust and efficient multi-modal task-oriented communication framework that integrate… ▽ More Semantic communications for multi-modal data can transmit task-relevant information efficiently over noisy and bandwidth-limited channels. However, a key challenge is to simultaneously compress inter-modal redundancy and improve semantic reliability under channel distortion. To address the challenge, we propose a robust and efficient multi-modal task-oriented communication framework that integrates a two-stage variational information bottleneck (VIB) with mutual information (MI) redundancy minimization. In the first stage, we apply uni-modal VIB to compress each modality separately, i.e., text, audio, and video, while preserving task-specific features. To enhance efficiency, an MI minimization module with adversarial training is then used to suppress cross-modal dependencies and to promote complementarity rather than redundancy. In the second stage, a multi-modal VIB is further used to compress the fused representation and to enhance robustness against channel distortion. Experimental results on multi-modal emotion recognition tasks demonstrate that the proposed framework significantly outperforms existing baselines in accuracy and reliability, particularly under low signal-to-noise ratio regimes. Our work provides a principled framework that jointly optimizes modality-specific compression, inter-modal redundancy, and communication reliability. △ Less

Submitted 10 November, 2025; originally announced November 2025.

Privacy Guarantee for Nash Equilibrium Computation of Aggregative Games Based on Pointwise Maximal Leakage

Authors: Zhaoyang Cheng, Guanpu Chen, Tobias J. Oechtering, Mikael Skoglund

Abstract: Privacy preservation has served as a key metric in designing Nash equilibrium (NE) computation algorithms. Although differential privacy (DP) has been widely employed for privacy guarantees, it does not exploit prior distributional knowledge of datasets and is ineffective in assessing information leakage for correlated datasets. To address these concerns, we establish a pointwise maximal leakage (… ▽ More Privacy preservation has served as a key metric in designing Nash equilibrium (NE) computation algorithms. Although differential privacy (DP) has been widely employed for privacy guarantees, it does not exploit prior distributional knowledge of datasets and is ineffective in assessing information leakage for correlated datasets. To address these concerns, we establish a pointwise maximal leakage (PML) framework when computing NE in aggregative games. By incorporating prior knowledge of players' cost function datasets, we obtain a precise and computable upper bound of privacy leakage with PML guarantees. In the entire view, we show PML refines DP by offering a tighter privacy guarantee, enabling flexibility in designing NE computation with prior knowledge. Also, in the individual view, we reveal that the lower bound of PML can exceed the upper bound of DP by constructing specific correlated datasets. The results emphasize that PML is a more proper privacy measure than DP since the latter fails to adequately capture privacy leakage in correlated datasets. Moreover, we conduct experiments with adversaries who attempt to infer players' private information to illustrate the effectiveness. △ Less

Submitted 9 June, 2026; v1 submitted 24 October, 2025; originally announced October 2025.

Risk level dependent Minimax Quantile lower bounds for Interactive Statistical Decision Making

Authors: Raghav Bongole, Amirreza Zamani, Tobias J. Oechtering, Mikael Skoglund

Abstract: Minimax risk and regret focus on expectation, missing rare failures critical in safety-critical bandits and reinforcement learning. Minimax quantiles capture these tails. Three strands of prior work motivate this study: minimax-quantile bounds restricted to non-interactive estimation; unified interactive analyses that focus on expected risk rather than risk level specific quantile bounds; and high… ▽ More Minimax risk and regret focus on expectation, missing rare failures critical in safety-critical bandits and reinforcement learning. Minimax quantiles capture these tails. Three strands of prior work motivate this study: minimax-quantile bounds restricted to non-interactive estimation; unified interactive analyses that focus on expected risk rather than risk level specific quantile bounds; and high-probability bandit bounds that still lack a quantile-specific toolkit for general interactive protocols. To close this gap, within the interactive statistical decision making framework, we develop high-probability Fano and Le Cam tools and derive risk level explicit minimax-quantile bounds, including a quantile-to-expectation conversion and a tight link between strict and lower minimax quantiles. Instantiating these results for the two-armed Gaussian bandit immediately recovers optimal-rate bounds. △ Less

Submitted 7 October, 2025; originally announced October 2025.

Privacy Mechanism Design based on Empirical Distributions

Authors: Leonhard Grosse, Sara Saeidian, Mikael Skoglund, Tobias J. Oechtering

Abstract: Pointwise maximal leakage (PML) is a per-outcome privacy measure based on threat models from quantitative information flow. Privacy guarantees with PML rely on knowledge about the distribution that generated the private data. In this work, we propose a framework for PML privacy assessment and mechanism design with empirical estimates of this data-generating distribution. By extending the PML frame… ▽ More Pointwise maximal leakage (PML) is a per-outcome privacy measure based on threat models from quantitative information flow. Privacy guarantees with PML rely on knowledge about the distribution that generated the private data. In this work, we propose a framework for PML privacy assessment and mechanism design with empirical estimates of this data-generating distribution. By extending the PML framework to consider sets of data-generating distributions, we arrive at bounds on the worst-case leakage within a given set. We use these bounds alongside large-deviation bounds from the literature to provide a method for obtaining distribution-independent $(\varepsilon,δ)$-PML guarantees when the data-generating distribution is estimated from available data samples. We provide an optimal binary mechanism, and show that mechanism design with this type of uncertainty about the data-generating distribution reduces to a linearly constrained convex program. Further, we show that optimal mechanisms designed for a distribution estimate can be used. Finally, we apply these tools to leakage assessment of the Laplace mechanism and the Gaussian mechanism for binary private data, and numerically show that the presented approach to mechanism design can yield significant utility increase compared to local differential privacy, while retaining similar privacy guarantees. △ Less

Submitted 26 September, 2025; originally announced September 2025.

Comments: accepted to IEEE CSF 2026

AI Safety Assurance in Electric Vehicles: A Case Study on AI-Driven SOC Estimation

Authors: Martin Skoglund, Fredrik Warg, Aria Mirzai, Anders Thorsen, Karl Lundgren, Peter Folkesson, Bastian Havers-zulka

Abstract: Integrating Artificial Intelligence (AI) technology in electric vehicles (EV) introduces unique challenges for safety assurance, particularly within the framework of ISO 26262, which governs functional safety in the automotive domain. Traditional assessment methodologies are not geared toward evaluating AI-based functions and require evolving standards and practices. This paper explores how an ind… ▽ More Integrating Artificial Intelligence (AI) technology in electric vehicles (EV) introduces unique challenges for safety assurance, particularly within the framework of ISO 26262, which governs functional safety in the automotive domain. Traditional assessment methodologies are not geared toward evaluating AI-based functions and require evolving standards and practices. This paper explores how an independent assessment of an AI component in an EV can be achieved when combining ISO 26262 with the recently released ISO/PAS 8800, whose scope is AI safety for road vehicles. The AI-driven State of Charge (SOC) battery estimation exemplifies the process. Key features relevant to the independent assessment of this extended evaluation approach are identified. As part of the evaluation, robustness testing of the AI component is conducted using fault injection experiments, wherein perturbed sensor inputs are systematically introduced to assess the component's resilience to input variance. △ Less

Submitted 3 September, 2025; originally announced September 2025.

Comments: 12 pages, 9 figures, EVS38, https://evs38-program.org/en/evs-38-proceedings/all

Methodology for Test Case Allocation based on a Formalized ODD

Authors: Martin Skoglund, Fredrik Warg, Anders Thoren, Sasikumar Punnekkat, Hans Hansson

Abstract: The emergence of Connected, Cooperative, and Automated Mobility (CCAM) systems has significantly transformed the safety assessment landscape. Because they integrate automated vehicle functions beyond those managed by a human driver, new methods are required to evaluate their safety. Approaches that compile evidence from multiple test environments have been proposed for type-approval and similar ev… ▽ More The emergence of Connected, Cooperative, and Automated Mobility (CCAM) systems has significantly transformed the safety assessment landscape. Because they integrate automated vehicle functions beyond those managed by a human driver, new methods are required to evaluate their safety. Approaches that compile evidence from multiple test environments have been proposed for type-approval and similar evaluations, emphasizing scenario coverage within the systems Operational Design Domain (ODD). However, aligning diverse test environment requirements with distinct testing capabilities remains challenging. This paper presents a method for evaluating the suitability of test case allocation to various test environments by drawing on and extending an existing ODD formalization with key testing attributes. The resulting construct integrates ODD parameters and additional test attributes to capture a given test environments relevant capabilities. This approach supports automatic suitability evaluation and is demonstrated through a case study on an automated reversing truck function. The system's implementation fidelity is tied to ODD parameters, facilitating automated test case allocation based on each environments capacity for object-detection sensor assessment. △ Less

Submitted 2 September, 2025; originally announced September 2025.

Comments: 12 pages, 8 figures, DECSoS, SAFECOMP 2025

Formalizing Operational Design Domains with the Pkl Language

Authors: Martin Skoglund, Fredrik Warg, Anders Thorsén, Sasikumar Punnekkat, Hans Hansson

Abstract: The deployment of automated functions that can operate without direct human supervision has changed safety evaluation in domains seeking higher levels of automation. Unlike conventional systems that rely on human operators, these functions require new assessment frameworks to demonstrate that they do not introduce unacceptable risks under real-world conditions. To make a convincing safety claim, t… ▽ More The deployment of automated functions that can operate without direct human supervision has changed safety evaluation in domains seeking higher levels of automation. Unlike conventional systems that rely on human operators, these functions require new assessment frameworks to demonstrate that they do not introduce unacceptable risks under real-world conditions. To make a convincing safety claim, the developer must present a thorough justification argument, supported by evidence, that a function is free from unreasonable risk when operated in its intended context. The key concept relevant to the presented work is the intended context, often captured by an Operational Design Domain specification (ODD). ODD formalization is challenging due to the need to maintain flexibility in adopting diverse specification formats while preserving consistency and traceability and integrating seamlessly into the development, validation, and assessment. This paper presents a way to formalize an ODD in the Pkl language, addressing central challenges in specifying ODDs while improving usability through specialized configuration language features. The approach is illustrated with an automotive example but can be broadly applied to ensure rigorous assessments of operational contexts. △ Less

Submitted 2 September, 2025; originally announced September 2025.

Comments: 8 pages, 9 figures, IV 2025

Information-Theoretic Fairness with A Bounded Statistical Parity Constraint

Authors: Amirreza Zamani, Abolfazl Changizi, Ragnar Thobaben, Mikael Skoglund

Abstract: In this paper, we study an information-theoretic problem of designing a fair representation that attains bounded statistical (demographic) parity. More specifically, an agent uses some useful data $X$ to solve a task $T$. Since both $X$ and $T$ are correlated with some sensitive attribute or secret $S$, the agent designs a representation $Y$ that satisfies a bounded statistical parity and/or priva… ▽ More In this paper, we study an information-theoretic problem of designing a fair representation that attains bounded statistical (demographic) parity. More specifically, an agent uses some useful data $X$ to solve a task $T$. Since both $X$ and $T$ are correlated with some sensitive attribute or secret $S$, the agent designs a representation $Y$ that satisfies a bounded statistical parity and/or privacy leakage constraint, that is, such that $I(Y;S) \leq ε$. Here, we relax the perfect demographic (statistical) parity and consider a bounded-parity constraint. In this work, we design the representation $Y$ that maximizes the mutual information $I(Y;T)$ about the task while satisfying a bounded compression (or encoding rate) constraint, that is, ensuring that $I(Y;X) \leq r$. Simultaneously, $Y$ satisfies the bounded statistical parity constraint $I(Y;S) \leq ε$. To design $Y$, we use extended versions of the Functional Representation Lemma and the Strong Functional Representation Lemma which are based on randomization techniques and study the tightness of the obtained bounds in special cases. The main idea to derive the lower bounds is to use randomization over useful data $X$ or sensitive data $S$. Considering perfect demographic parity, i.e., $ε=0$, we improve the existing results (lower bounds) by using a tighter version of the Strong Functional Representation Lemma and propose new upper bounds. We then propose upper and lower bounds for the main problem and show that allowing non-zero leakage can improve the attained utility. Finally, we study the bounds and compare them in a numerical example. The problem studied in this paper can also be interpreted as one of code design with bounded leakage and bounded rate privacy considering the sensitive attribute as a secret. △ Less

Submitted 18 August, 2025; originally announced August 2025.

Coding-Enforced Robust Secure Aggregation for Federated Learning Under Unreliable Communication

Authors: Shudi Weng, Chao Ren, Yizhou Zhao, Ming Xiao, Mikael Skoglund

Abstract: This work studies privacy-preserving federated learning (ppFL) under unreliable communication. In ppFL, zero-sum privacy noises enables privacy protection without sacrificing model accuracy, effectively overcoming the privacy-utility trade-off. However, in practice, unreliable communication can randomly disrupt the coordination of zero-sum noises, leading to aggregation errors and unpredictable pa… ▽ More This work studies privacy-preserving federated learning (ppFL) under unreliable communication. In ppFL, zero-sum privacy noises enables privacy protection without sacrificing model accuracy, effectively overcoming the privacy-utility trade-off. However, in practice, unreliable communication can randomly disrupt the coordination of zero-sum noises, leading to aggregation errors and unpredictable partial participation, which severely harm the model accuracy and learning performance. To overcome these challenges, we propose a robust coding-enforced structured secure aggregation method, termed secure cooperative gradient coding (SecCoGC), which enables exact reconstruction of the global model under unreliable communication while allowing for arbitrarily strong privacy preservation. In this paper, a complete problem formulation and constructions of real-field zero-sum privacy noise are presented, and fairness is introduced as a privacy metric. Privacy across all protocol layers in SecCoGC is evaluated, accounting for the correlation among privacy noises and their linear combination under unreliable communication. Moreover, a distinct convergence analysis for the FL algorithm with a binary outcome for global model recovery is provided. Experimental results demonstrate that SecCoGC achieves strong resilience to unreliable communication while maintaining varying levels of privacy preservation, yielding test accuracy improvements of up to 20%-70% over existing benchmark methods. △ Less

Submitted 12 July, 2026; v1 submitted 10 July, 2025; originally announced July 2025.

Cooperative Gradient Coding

Authors: Shudi Weng, Ming Xiao, Chao Ren, Mikael Skoglund

Abstract: This work studies gradient coding (GC) in the context of distributed training problems with unreliable communication. We propose cooperative GC (CoGC), a novel gradient-sharing-based GC framework that leverages cooperative communication among clients. This approach ultimately eliminates the need for dataset replication, making it both communication- and computation-efficient and suitable for feder… ▽ More This work studies gradient coding (GC) in the context of distributed training problems with unreliable communication. We propose cooperative GC (CoGC), a novel gradient-sharing-based GC framework that leverages cooperative communication among clients. This approach ultimately eliminates the need for dataset replication, making it both communication- and computation-efficient and suitable for federated learning (FL). By employing the standard GC decoding mechanism, CoGC yields strictly binary outcomes: either the global model is exactly recovered, or the decoding fails entirely, with no intermediate results. This characteristic ensures the optimality of the training and demonstrates strong resilience to client-to-server communication failures when the communication channels among clients are in good condition. However, it may also result in communication inefficiency and hinder convergence due to its lack of flexibility, especially when communication channels among clients are in poor condition. To overcome this limitation and further harness the potential of GC matrices, we propose a complementary decoding mechanism, termed GC$^+$, which leverages information that would otherwise be discarded during GC decoding failures. This approach significantly improves system reliability under unreliable communication, as the full recovery of the global model typically dominates in GC$^+$. To conclude, this work establishes solid theoretical frameworks for both CoGC and GC$^+$. We provide complete outage analyses for each decoding mechanism, along with a rigorous investigation of how outages affect the structure and performance of GC matrices. Building on these analyses, we derive convergence bounds for both decoding mechanisms. Finally, the effectiveness of CoGC and GC$^+$ is validated through extensive simulations. △ Less

Submitted 7 July, 2025; originally announced July 2025.

Coded Robust Aggregation for Distributed Learning under Byzantine Attacks

Authors: Chengxi Li, Ming Xiao, Mikael Skoglund

Abstract: In this paper, we investigate the problem of distributed learning (DL) in the presence of Byzantine attacks. For this problem, various robust bounded aggregation (RBA) rules have been proposed at the central server to mitigate the impact of Byzantine attacks. However, current DL methods apply RBA rules for the local gradients from the honest devices and the disruptive information from Byzantine de… ▽ More In this paper, we investigate the problem of distributed learning (DL) in the presence of Byzantine attacks. For this problem, various robust bounded aggregation (RBA) rules have been proposed at the central server to mitigate the impact of Byzantine attacks. However, current DL methods apply RBA rules for the local gradients from the honest devices and the disruptive information from Byzantine devices, and the learning performance degrades significantly when the local gradients of different devices vary considerably from each other. To overcome this limitation, we propose a new DL method to cope with Byzantine attacks based on coded robust aggregation (CRA-DL). Before training begins, the training data are allocated to the devices redundantly. During training, in each iteration, the honest devices transmit coded gradients to the server computed from the allocated training data, and the server then aggregates the information received from both honest and Byzantine devices using RBA rules. In this way, the global gradient can be approximately recovered at the server to update the global model. Compared with current DL methods applying RBA rules, the improvement of CRA-DL is attributed to the fact that the coded gradients sent by the honest devices are closer to each other. This closeness enhances the robustness of the aggregation against Byzantine attacks, since Byzantine messages tend to be significantly different from those of honest devices in this case. We theoretically analyze the convergence performance of CRA-DL. Finally, we present numerical results to verify the superiority of the proposed method over existing baselines, showing its enhanced learning performance under Byzantine attacks. △ Less

Submitted 17 March, 2026; v1 submitted 17 May, 2025; originally announced June 2025.

Comments: C. Li, M. Xiao and M. Skoglund, "Coded Robust Aggregation for Distributed Learning Under Byzantine Attacks," in IEEE Transactions on Information Forensics and Security, vol. 20, pp. 11636-11651, 2025, doi: 10.1109/TIFS.2025.3624620

Heterogeneity-Aware Client Sampling for Optimal and Efficient Federated Learning

Authors: Shudi Weng, Chao Ren, Ming Xiao, Mikael Skoglund

Abstract: Federated learning (FL) commonly involves clients with diverse communication and computational capabilities. Such heterogeneity can significantly distort the optimization dynamics and lead to objective inconsistency, where the global model converges to an incorrect stationary point potentially far from the pursued optimum. Despite its critical impact, the joint effect of communication and computat… ▽ More Federated learning (FL) commonly involves clients with diverse communication and computational capabilities. Such heterogeneity can significantly distort the optimization dynamics and lead to objective inconsistency, where the global model converges to an incorrect stationary point potentially far from the pursued optimum. Despite its critical impact, the joint effect of communication and computation heterogeneity has remained largely unexplored, due to the intrinsic complexity of their interaction. In this paper, we reveal the fundamentally distinct mechanisms through which heterogeneous communication and computation drive inconsistency in FL. To the best of our knowledge, this is the first unified theoretical analysis of general heterogeneous FL, offering a principled understanding of how these two forms of heterogeneity jointly distort the optimization trajectory under arbitrary choices of local solvers. Motivated by these insights, we propose Federated Heterogeneity-Aware Client Sampling, FedACS, a universal method to eliminate all types of objective inconsistency. We theoretically prove that FedACS converges to the correct optimum at a rate of $O(1/\sqrt{R})$, even in dynamic heterogeneous environments. Extensive experiments across multiple datasets show that FedACS outperforms state-of-the-art and category-specific baselines by 4.3%-36%, while reducing communication costs by 22%-89% and computation loads by 14%-105%, respectively. △ Less

Submitted 22 February, 2026; v1 submitted 16 May, 2025; originally announced May 2025.

The Larger the Merrier? Efficient Large AI Model Inference in Wireless Edge Networks

Authors: Zhonghao Lyu, Ming Xiao, Jie Xu, Mikael Skoglund, Marco Di Renzo

Abstract: The growing demand for large artificial intelligence model (LAIM) services is driving a paradigm shift from traditional cloud-based inference to edge-based inference for low-latency, privacy-preserving applications. In particular, edge-device co-inference, which partitions LAIMs between edge devices and servers, has emerged as a promising strategy for resource-efficient LAIM execution in wireless… ▽ More The growing demand for large artificial intelligence model (LAIM) services is driving a paradigm shift from traditional cloud-based inference to edge-based inference for low-latency, privacy-preserving applications. In particular, edge-device co-inference, which partitions LAIMs between edge devices and servers, has emerged as a promising strategy for resource-efficient LAIM execution in wireless networks. In this paper, we investigate a pruning-aware LAIM co-inference scheme, where a pre-trained LAIM is pruned and partitioned into on-device and on-server sub-models for deployment. For analysis, we first prove that the LAIM output distortion is upper bounded by its parameter distortion. Then, we derive a lower bound on parameter distortion via rate-distortion theory, analytically capturing the relationship between pruning ratio and co-inference performance. Next, based on the analytical results, we formulate an LAIM co-inference distortion bound minimization problem by jointly optimizing the pruning ratio, transmit power, and computation frequency under system latency, energy, and available resource constraints. Moreover, we propose an efficient algorithm to tackle the considered highly non-convex problem. Finally, extensive simulations demonstrate the effectiveness of the proposed design. In particular, model parameter distortion is shown to provide a reliable bound on output distortion. Also, the proposed joint pruning ratio and resource management design achieves superior performance in balancing trade-offs among inference performance, system latency, and energy consumption compared with benchmark schemes, such as fully on-device and on-server inference. Moreover, the split point is shown to play a critical role in system performance optimization under heterogeneous and resource-limited edge environments. △ Less

Submitted 14 May, 2025; originally announced May 2025.

Refined PAC-Bayes Bounds for Offline Bandits

Authors: Amaury Gouverneur, Tobias J. Oechtering, Mikael Skoglund

Abstract: In this paper, we present refined probabilistic bounds on empirical reward estimates for off-policy learning in bandit problems. We build on the PAC-Bayesian bounds from Seldin et al. (2010) and improve on their results using a new parameter optimization approach introduced by Rodríguez et al. (2024). This technique is based on a discretization of the space of possible events to optimize the "in p… ▽ More In this paper, we present refined probabilistic bounds on empirical reward estimates for off-policy learning in bandit problems. We build on the PAC-Bayesian bounds from Seldin et al. (2010) and improve on their results using a new parameter optimization approach introduced by Rodríguez et al. (2024). This technique is based on a discretization of the space of possible events to optimize the "in probability" parameter. We provide two parameter-free PAC-Bayes bounds, one based on Hoeffding-Azuma's inequality and the other based on Bernstein's inequality. We prove that our bounds are almost optimal as they recover the same rate as would be obtained by setting the "in probability" parameter after the realization of the data. △ Less

Submitted 17 February, 2025; originally announced February 2025.

Comments: 6 pages

Integrated Sensing and Communication with Distributed Rate-Limited Helpers

Authors: Yiqi Chen, Holger Boche, Tobias J. Oechtering, Mikael Skoglund

Abstract: This paper studies integrated sensing and communication (ISAC) systems with two rate-limited helpers who observe the channel state sequence and the feedback sequence, respectively. Depending on the timing of compressing and using the state information, our proposed coding scheme gives an inner bound of the capacity-compression-distortion tradeoff region. The tradeoff is realized by sending part of… ▽ More This paper studies integrated sensing and communication (ISAC) systems with two rate-limited helpers who observe the channel state sequence and the feedback sequence, respectively. Depending on the timing of compressing and using the state information, our proposed coding scheme gives an inner bound of the capacity-compression-distortion tradeoff region. The tradeoff is realized by sending part of the state information at the beginning of the transmission to facilitate the communication and compressing the remaining part together with the feedback signal. The inner bound becomes tight bounds in several special cases. △ Less

Submitted 13 February, 2025; originally announced February 2025.

Comments: Part of the results were accepted by ICC2025

Evaluating Differential Privacy on Correlated Datasets Using Pointwise Maximal Leakage

Authors: Sara Saeidian, Tobias J. Oechtering, Mikael Skoglund

Abstract: Data-driven advancements significantly contribute to societal progress, yet they also pose substantial risks to privacy. In this landscape, differential privacy (DP) has become a cornerstone in privacy preservation efforts. However, the adequacy of DP in scenarios involving correlated datasets has sometimes been questioned and multiple studies have hinted at potential vulnerabilities. In this work… ▽ More Data-driven advancements significantly contribute to societal progress, yet they also pose substantial risks to privacy. In this landscape, differential privacy (DP) has become a cornerstone in privacy preservation efforts. However, the adequacy of DP in scenarios involving correlated datasets has sometimes been questioned and multiple studies have hinted at potential vulnerabilities. In this work, we delve into the nuances of applying DP to correlated datasets by leveraging the concept of pointwise maximal leakage (PML) for a quantitative assessment of information leakage. Our investigation reveals that DP's guarantees can be arbitrarily weak for correlated databases when assessed through the lens of PML. More precisely, we prove the existence of a pure DP mechanism with PML levels arbitrarily close to that of a mechanism which releases individual entries from a database without any perturbation. By shedding light on the limitations of DP on correlated datasets, our work aims to foster a deeper understanding of subtle privacy risks and highlight the need for the development of more effective privacy-preserving mechanisms tailored to diverse scenarios. △ Less

Submitted 8 February, 2025; originally announced February 2025.

Comments: Published in the proceedings of the Annual Privacy Forum (APF) 2024

An Information-Theoretic Analysis of Thompson Sampling with Infinite Action Spaces

Authors: Amaury Gouverneur, Borja Rodriguez Gálvez, Tobias Oechtering, Mikael Skoglund

Abstract: This paper studies the Bayesian regret of the Thompson Sampling algorithm for bandit problems, building on the information-theoretic framework introduced by Russo and Van Roy (2015). Specifically, it extends the rate-distortion analysis of Dong and Van Roy (2018), which provides near-optimal bounds for linear bandits. A limitation of these results is the assumption of a finite action space. We add… ▽ More This paper studies the Bayesian regret of the Thompson Sampling algorithm for bandit problems, building on the information-theoretic framework introduced by Russo and Van Roy (2015). Specifically, it extends the rate-distortion analysis of Dong and Van Roy (2018), which provides near-optimal bounds for linear bandits. A limitation of these results is the assumption of a finite action space. We address this by extending the analysis to settings with infinite and continuous action spaces. Additionally, we specialize our results to bandit problems with expected rewards that are Lipschitz continuous with respect to the action space, deriving a regret bound that explicitly accounts for the complexity of the action space. △ Less

Submitted 4 February, 2025; originally announced February 2025.

Comments: 5 pages, accepted to ICASSP

Multi-terminal Strong Coordination over Noisy Channels with Encoder Co-operation

Authors: Viswanathan Ramachandran, Tobias J. Oechtering, Mikael Skoglund

Abstract: We investigate the problem of strong coordination over a multiple-access channel (MAC) with cribbing encoders. In this configuration, two encoders observe independent and identically distributed (i.i.d.) samples of a source random variable each and encode the inputs to the MAC. The decoder which observes the output of the MAC together with side-information, must generate approximately i.i.d. sampl… ▽ More We investigate the problem of strong coordination over a multiple-access channel (MAC) with cribbing encoders. In this configuration, two encoders observe independent and identically distributed (i.i.d.) samples of a source random variable each and encode the inputs to the MAC. The decoder which observes the output of the MAC together with side-information, must generate approximately i.i.d. samples of another random variable which is jointly distributed with the two sources and the side information. We also allow for possible encoder cooperation, where one of the encoders can non-causally crib from the other encoders input. Independent pairwise shared randomness is assumed between each encoder and the decoder at limited rates. Firstly, in the presence of cribbing, we derive an achievable region based on joint source-channel coding. We also prove that in the absence of cribbing, our inner bound is tight for the special case when the MAC is composed of deterministic links, and the sources are conditionally independent given the side information. We then explicitly compute the regions for an example both with and without cribbing between the encoders, and demonstrate that cribbing strictly improves upon the achievable region. △ Less

Submitted 5 June, 2025; v1 submitted 21 January, 2025; originally announced January 2025.

Comments: Updated Theorem 2. 7 pages, 1 figure. arXiv admin note: substantial text overlap with arXiv:2411.14123

An Information Geometric Approach to Local Information Privacy with Applications to Max-lift and Local Differential Privacy

Authors: Amirreza Zamani, Parastoo Sadeghi, Mikael Skoglund

Abstract: We study an information-theoretic privacy mechanism design, where an agent observes useful data $Y$ and wants to reveal the information to a user. Since the useful data is correlated with the private data $X$, the agent uses a privacy mechanism to produce disclosed data $U$ that can be released. We assume that the agent observes $Y$ and has no direct access to $X$, i.e., the private data is hidden… ▽ More We study an information-theoretic privacy mechanism design, where an agent observes useful data $Y$ and wants to reveal the information to a user. Since the useful data is correlated with the private data $X$, the agent uses a privacy mechanism to produce disclosed data $U$ that can be released. We assume that the agent observes $Y$ and has no direct access to $X$, i.e., the private data is hidden. We study the privacy mechanism design that maximizes the revealed information about $Y$ while satisfying a bounded Local Information Privacy (LIP) criterion. When the leakage is sufficiently small, concepts from information geometry allow us to locally approximate the mutual information. By utilizing this approximation the main privacy-utility trade-off problem can be rewritten as a quadratic optimization problem that has closed-form solution under some constraints. For the cases where the closed-form solution is not obtained we provide lower bounds on it. In contrast to the previous works that have complexity issues, here, we provide simple privacy designs with low complexity which are based on finding the maximum singular value and singular vector of a matrix. To do so, we follow two approaches where in the first one we find a lower bound on the main problem and then approximate it, however, in the second approach we approximate the main problem directly. In this work, we present geometrical interpretations of the proposed methods and in a numerical example we compare our results considering both approaches with the optimal solution and the previous methods. Furthermore, we discuss how our method can be generalized considering larger amounts for the privacy leakage. Finally, we discuss how the proposed methods can be applied to deal with differential privacy. △ Less

Submitted 20 January, 2025; originally announced January 2025.

Bounds on the privacy amplification of arbitrary channels via the contraction of $f_α$-divergence

Authors: Leonhard Grosse, Sara Saeidian, Tobias J. Oechtering, Mikael Skoglund

Abstract: We examine the privacy amplification of channels that do not necessarily satisfy any LDP guarantee by analyzing their contraction behavior in terms of $f_α$-divergence, an $f$-divergence related to Rényi-divergence via a monotonic transformation. We present bounds on contraction for restricted sets of prior distributions via $f$-divergence inequalities and present an improved Pinsker's inequality… ▽ More We examine the privacy amplification of channels that do not necessarily satisfy any LDP guarantee by analyzing their contraction behavior in terms of $f_α$-divergence, an $f$-divergence related to Rényi-divergence via a monotonic transformation. We present bounds on contraction for restricted sets of prior distributions via $f$-divergence inequalities and present an improved Pinsker's inequality for $f_α$-divergence based on the joint range technique by Harremoës and Vajda. The presented bound is tight whenever the value of the total variation distance is larger than 1/$α$. By applying these inequalities in a cross-channel setting, we arrive at strong data processing inequalities for $f_α$-divergence that can be adapted to use-case specific restrictions of input distributions and channel. The application of these results to privacy amplification shows that even very sparse channels can lead to significant privacy amplification when used as a post-processing step after local differentially private mechanisms. △ Less

Submitted 25 November, 2025; v1 submitted 20 January, 2025; originally announced January 2025.

Comments: 2025 61st Allerton Conference on Communication, Control, and Computing Proceedings, see https://hdl.handle.net/2142/130261

Reinforcement Learning Based Goodput Maximization with Quantized Feedback in URLLC

Authors: Hasan Basri Celebi, Mikael Skoglund

Abstract: This paper presents a comprehensive system model for goodput maximization with quantized feedback in Ultra-Reliable Low-Latency Communication (URLLC), focusing on dynamic channel conditions and feedback schemes. The study investigates a communication system, where the receiver provides quantized channel state information to the transmitter. The system adapts its feedback scheme based on reinforcem… ▽ More This paper presents a comprehensive system model for goodput maximization with quantized feedback in Ultra-Reliable Low-Latency Communication (URLLC), focusing on dynamic channel conditions and feedback schemes. The study investigates a communication system, where the receiver provides quantized channel state information to the transmitter. The system adapts its feedback scheme based on reinforcement learning, aiming to maximize goodput while accommodating varying channel statistics. We introduce a novel Rician-$K$ factor estimation technique to enable the communication system to optimize the feedback scheme. This dynamic approach increases the overall performance, making it well-suited for practical URLLC applications where channel statistics vary over time. △ Less

Submitted 19 January, 2025; originally announced January 2025.

Comments: Accepted for the IARIA 21st International Conference on Wireless and Mobile Communication (ICWMC 2025) Conference

Private Semantic Communications with Separate Blind Encoders

Authors: Amirreza Zamani, Mikael Skoglund

Abstract: We study a semantic communication problem with a privacy constraint where an encoder consists of two separate parts, e.g., encoder 1 and encoder 2. The first encoder has access to information source $X=(X_1,\ldots,X_N)$ which is arbitrarily correlated with private data $S$. The private data is not accessible by encoder 1, however, the second encoder has access to it and the output of encoder 1. A… ▽ More We study a semantic communication problem with a privacy constraint where an encoder consists of two separate parts, e.g., encoder 1 and encoder 2. The first encoder has access to information source $X=(X_1,\ldots,X_N)$ which is arbitrarily correlated with private data $S$. The private data is not accessible by encoder 1, however, the second encoder has access to it and the output of encoder 1. A user asks for a task $h(X)$ and the first encoder designs the semantic of the information source $f(X)$ to disclose. Due to the privacy constraints $f(X)$ can not be revealed directly to the user and the second encoder applies a statistical privacy mechanism to produce disclosed data $U$. Here, we assume that encoder 2 has no access to the task and the design of the disclosed data is based on the semantic and the private data. In this work, we propose a novel approach where $U$ is produced by solving a privacy-utility trade-off based on the semantic and the private data. We design $U$ utilizing different methods such as using extended versions of the Functional Representation Lemma and the Strong Functional Representation Lemma. We evaluate our design by computing the utility attained by the user. Finally, we study and compare the obtained bounds in a numerical example. △ Less

Submitted 23 December, 2024; originally announced December 2024.

An Information-Theoretic Analysis of Thompson Sampling for Logistic Bandits

Authors: Amaury Gouverneur, Borja Rodríguez-Gálvez, Tobias J. Oechtering, Mikael Skoglund

Abstract: We study the performance of the Thompson Sampling algorithm for logistic bandit problems. In this setting, an agent receives binary rewards with probabilities determined by a logistic function, $\exp(β\langle a, θ\rangle)/(1+\exp(β\langle a, θ\rangle))$, with slope parameter $β>0$, and where both the action $a\in \mathcal{A}$ and parameter $θ\in \mathcal{O}$ lie within the $d$-dimensional unit bal… ▽ More We study the performance of the Thompson Sampling algorithm for logistic bandit problems. In this setting, an agent receives binary rewards with probabilities determined by a logistic function, $\exp(β\langle a, θ\rangle)/(1+\exp(β\langle a, θ\rangle))$, with slope parameter $β>0$, and where both the action $a\in \mathcal{A}$ and parameter $θ\in \mathcal{O}$ lie within the $d$-dimensional unit ball. Adopting the information-theoretic framework introduced by Russo and Van Roy (2016), we analyze the information ratio, a statistic that quantifies the trade-off between the immediate regret incurred and the information gained about the optimal action. We improve upon previous results by establishing that the information ratio is bounded by $\tfrac{9}{2}dα^{-2}$, where $α$ is a minimax measure of the alignment between the action space $\mathcal{A}$ and the parameter space $\mathcal{O}$, and is independent of $β$. Using this result, we derive a bound of order $O(d/α\sqrt{T \log(βT/d)})$ on the Bayesian expected regret of Thompson Sampling incurred after $T$ time steps. To our knowledge, this is the first regret bound for logistic bandits that depends only logarithmically on $β$ while being independent of the number of actions. In particular, when the action space contains the parameter space, the bound on the expected regret is of order $\tilde{O}(d \sqrt{T})$. △ Less

Submitted 20 February, 2025; v1 submitted 3 December, 2024; originally announced December 2024.

Comments: 21 pages, under review

Multi-terminal Strong Coordination subject to Secrecy Constraints

Authors: Viswanathan Ramachandran, Tobias J. Oechtering, Mikael Skoglund

Abstract: A fundamental problem in decentralized networked systems is to coordinate actions of different agents so that they reach a state of agreement. In such applications, it is additionally desirable that the actions at various nodes may not be anticipated by malicious eavesdroppers. Motivated by this, we investigate the problem of secure multi-terminal strong coordination aided by a multiple-access wir… ▽ More A fundamental problem in decentralized networked systems is to coordinate actions of different agents so that they reach a state of agreement. In such applications, it is additionally desirable that the actions at various nodes may not be anticipated by malicious eavesdroppers. Motivated by this, we investigate the problem of secure multi-terminal strong coordination aided by a multiple-access wiretap channel. In this setup, independent and identically distributed copies of correlated sources are observed by two transmitters who encode the channel inputs to the MAC-WT. The legitimate receiver observing the channel output and side information correlated with the sources must produce approximately i.i.d. copies of an output variable jointly distributed with the sources. Furthermore, we demand that an external eavesdropper learns essentially nothin g about the sources and the simulated output sequence by observing its own MAC-WT output. This setting is aided by the presence of independent pairwise shared randomness between each encoder and the legitimate decoder, that is unavailable to the eavesdropper. We derive an achievable rate region based on a combination of coordination coding and wiretap coding, along with an outer bound. The inner bound is shown to be tight and a complete characterization is derived for the special case when the sources are conditionally independent given the decoder side information and the legitimate channel is composed of deterministic links. Further, we also analyze a more general scenario with possible encoder cooperation, where one of the encoders can non-causally crib from the other encoders input, for which an achievable rate region is proposed. We then explicitly compute the rate regions for an example both with and without cribbing between the encoders, and demonstrate that cribbing strictly improves upon the achievable rate region. △ Less

Submitted 21 November, 2024; originally announced November 2024.

Comments: Extended version of ISIT 2024 paper

Information-Theoretic Minimax Regret Bounds for Reinforcement Learning based on Duality

Authors: Raghav Bongole, Amaury Gouverneur, Borja Rodríguez-Gálvez, Tobias J. Oechtering, Mikael Skoglund

Abstract: We study agents acting in an unknown environment where the agent's goal is to find a robust policy. We consider robust policies as policies that achieve high cumulative rewards for all possible environments. To this end, we consider agents minimizing the maximum regret over different environment parameters, leading to the study of minimax regret. This research focuses on deriving information-theor… ▽ More We study agents acting in an unknown environment where the agent's goal is to find a robust policy. We consider robust policies as policies that achieve high cumulative rewards for all possible environments. To this end, we consider agents minimizing the maximum regret over different environment parameters, leading to the study of minimax regret. This research focuses on deriving information-theoretic bounds for minimax regret in Markov Decision Processes (MDPs) with a finite time horizon. Building on concepts from supervised learning, such as minimum excess risk (MER) and minimax excess risk, we use recent bounds on the Bayesian regret to derive minimax regret bounds. Specifically, we establish minimax theorems and use bounds on the Bayesian regret to perform minimax regret analysis using these minimax theorems. Our contributions include defining a suitable minimax regret in the context of MDPs, finding information-theoretic bounds for it, and applying these bounds in various scenarios. △ Less

Submitted 21 October, 2024; originally announced October 2024.

Extended Functional Representation Lemma: A Tool For Privacy, Semantic Representation, Caching, and Compression Design

Authors: Amirreza Zamani, Mikael Skoglund

Abstract: This paper provides an overview of a problem in information-theoretic privacy mechanism design, addressing two scenarios in which private data is either observable or hidden. In each scenario, different privacy measures are used, including bounded mutual information and two types of per-letter privacy constraints. Considering the first scenario, an agent observes useful data that is correlated wit… ▽ More This paper provides an overview of a problem in information-theoretic privacy mechanism design, addressing two scenarios in which private data is either observable or hidden. In each scenario, different privacy measures are used, including bounded mutual information and two types of per-letter privacy constraints. Considering the first scenario, an agent observes useful data that is correlated with private data, and wants to disclose the useful information to a user. Due to the privacy concerns, direct disclosure is prohibited. Hence, a privacy mechanism is designed to generate disclosed data which maximizes the revealed information about the useful data while satisfying a privacy constraint. In the second scenario, the agent has additionally access to the private data. We discuss how the Functional Representation Lemma, the Strong Functional Representation Lemma, and their extended versions are useful for designing low-complexity privacy mechanisms that achieve optimal privacy-utility trade-offs under certain constraints. Furthermore, another privacy design problem is presented where part of the private attribute is more private than the remaining part. Finally, we provide applications including semantic communications, caching and delivery, and compression designs, where the approach can be applied. △ Less

Submitted 7 October, 2024; originally announced October 2024.

Comments: arXiv admin note: text overlap with arXiv:2212.12475

Improving Achievability of Cache-Aided Private Variable-Length Coding with Zero Leakage

Authors: Amirreza Zamani, Mikael Skoglund

Abstract: A statistical cache-aided compression problem with a privacy constraint is studied, where a server has access to a database of $N$ files, $(Y_1,...,Y_N)$, each of size $F$ bits and is linked through a shared channel to $K$ users, where each has access to a local cache memory of size $MF$ bits. During the placement phase, the server fills the users' caches without prior knowledge of their demands,… ▽ More A statistical cache-aided compression problem with a privacy constraint is studied, where a server has access to a database of $N$ files, $(Y_1,...,Y_N)$, each of size $F$ bits and is linked through a shared channel to $K$ users, where each has access to a local cache memory of size $MF$ bits. During the placement phase, the server fills the users' caches without prior knowledge of their demands, while the delivery phase takes place after the users send their demands to the server. We assume that each file in database $Y_i$ is arbitrarily correlated with a private attribute $X$, and an adversary is assumed to have access to the shared channel. The users and the server have access to a shared key $W$. The goal is to design the cache contents and the delivered message $\cal C$ such that the average length of $\mathcal{C}$ is minimized, while satisfying: i. The response $\cal C$ does not reveal any information about $X$, i.e., $I(X;\mathcal{C})=0$; ii. User $i$ can decode its demand, $Y_{d_i}$, by using the shared key $W$, $\cal C$, and its local cache $Z_i$. In a previous work, we have proposed a variable-length coding scheme that combines privacy-aware compression with coded caching techniques. In this paper, we propose a new achievability scheme using minimum entropy coupling concept and a greedy entropy-based algorithm. We show that the proposed scheme improves the previous results. Moreover, considering two special cases we improve the obtained bounds using the common information concept. △ Less

Submitted 30 September, 2024; originally announced September 2024.

An Information-Theoretic Approach to Generalization Theory

Authors: Borja Rodríguez-Gálvez, Ragnar Thobaben, Mikael Skoglund

Abstract: We investigate the in-distribution generalization of machine learning algorithms. We depart from traditional complexity-based approaches by analyzing information-theoretic bounds that quantify the dependence between a learning algorithm and the training data. We consider two categories of generalization guarantees: 1) Guarantees in expectation: These bounds measure performance in the average cas… ▽ More We investigate the in-distribution generalization of machine learning algorithms. We depart from traditional complexity-based approaches by analyzing information-theoretic bounds that quantify the dependence between a learning algorithm and the training data. We consider two categories of generalization guarantees: 1) Guarantees in expectation: These bounds measure performance in the average case. Here, the dependence between the algorithm and the data is often captured by information measures. While these measures offer an intuitive interpretation, they overlook the geometry of the algorithm's hypothesis class. Here, we introduce bounds using the Wasserstein distance to incorporate geometry, and a structured, systematic method to derive bounds capturing the dependence between the algorithm and an individual datum, and between the algorithm and subsets of the training data. 2) PAC-Bayesian guarantees: These bounds measure the performance level with high probability. Here, the dependence between the algorithm and the data is often measured by the relative entropy. We establish connections between the Seeger--Langford and Catoni's bounds, revealing that the former is optimized by the Gibbs posterior. We introduce novel, tighter bounds for various types of loss functions. To achieve this, we introduce a new technique to optimize parameters in probabilistic statements. To study the limitations of these approaches, we present a counter-example where most of the information-theoretic bounds fail while traditional approaches do not. Finally, we explore the relationship between privacy and generalization. We show that algorithms with a bounded maximal leakage generalize. For discrete data, we derive new bounds for differentially private algorithms that guarantee generalization even with a constant privacy parameter, which is in contrast to previous bounds in the literature. △ Less

Submitted 20 August, 2024; originally announced August 2024.