Showing 1–20 of 20 results for author: Ferguson, A

Identifying potentiating events in evolutionary search using replay experiments

Authors: Austin J. Ferguson, Alexander Lalejini

Abstract: In this work, we introduce analytical replay experiments to the evolutionary computing community. Replay experiments originated in the context of laboratory experimental evolution as an empirical approach to identifying potentiating events that increased the likelihood of an observed evolutionary outcome. By restarting a population's evolution from different historical time points, replay experime… ▽ More In this work, we introduce analytical replay experiments to the evolutionary computing community. Replay experiments originated in the context of laboratory experimental evolution as an empirical approach to identifying potentiating events that increased the likelihood of an observed evolutionary outcome. By restarting a population's evolution from different historical time points, replay experiments sample the distribution of what could have evolved from different points in time, which allows us to quantify how a population's potential for different evolutionary outcomes changed as a result of that population's history. In this work, we give a step-by-step guide to designing replay experiments for evolutionary computing systems. We then provide a demonstrative example replay experiment that measures how potentiation for problem-solving success changed in an evolved genetic programming population, showing that increases in potential for success do not necessarily correspond with increases in a population's fitness. Broadly, we argue that analytical replay experiments can be a powerful tool for expanding the theoretical foundations of evolutionary computing, and we offer suggestions for promising future research directions enabled by replay experiments. △ Less

Submitted 10 August, 2026; originally announced August 2026.

UNet-Based Keypoint Regression for 3D Cone Localization in Autonomous Racing

Authors: Mariia Baidachna, James Carty, Aidan Ferguson, Joseph Agrane, Varad Kulkarni, Aubrey Agub, Michael Baxendale, Aaron David, Rachel Horton, Elliott Atkinson

Abstract: Accurate cone localization in 3D space is essential in autonomous racing for precise navigation around the track. Approaches that rely on traditional computer vision algorithms are sensitive to environmental variations, and neural networks are often trained on limited data and are infeasible to run in real time. We present a UNet-based neural network for keypoint detection on cones, leveraging the… ▽ More Accurate cone localization in 3D space is essential in autonomous racing for precise navigation around the track. Approaches that rely on traditional computer vision algorithms are sensitive to environmental variations, and neural networks are often trained on limited data and are infeasible to run in real time. We present a UNet-based neural network for keypoint detection on cones, leveraging the largest custom-labeled dataset we have assembled. Our approach enables accurate cone position estimation and the potential for color prediction. Our model achieves substantial improvements in keypoint accuracy over conventional methods. Furthermore, we leverage our predicted keypoints in the perception pipeline and evaluate the end-to-end autonomous system. Our results show high-quality performance across all metrics, highlighting the effectiveness of this approach and its potential for adoption in competitive autonomous racing systems. △ Less

Submitted 25 February, 2026; originally announced February 2026.

Comments: 8 pages, 9 figures. Accepted to ICCV End-to-End 3D Learning Workshop 2025 and presented as a poster; not included in the final proceedings due to a conference administrative error

Controllable Diffusion-Based Lesion Inpainting for Scalable Histopathology Data Augmentation

Authors: Mohamad Koohi-Moghadam, Mohammad-Ali Nikouei Mahani, Rex K. H. Au-Yeung, Raymond Yu O, Monalyn Marabi, Piyapharom Intarawichian, Fabian Z. X. Lean, Andrew Ferguson, Kyongtae Tyler Bae

Abstract: Expert-annotated training data remains the critical bottleneck for AI in histopathology, particularly for rare pathologies where even dozens of cases may be unavailable. While data augmentation offers a solution, existing methods fail to generate sufficiently realistic lesion morphologies that preserve tissue-specific architectures. Here we present PathoGen, a diffusion-based generative model enab… ▽ More Expert-annotated training data remains the critical bottleneck for AI in histopathology, particularly for rare pathologies where even dozens of cases may be unavailable. While data augmentation offers a solution, existing methods fail to generate sufficiently realistic lesion morphologies that preserve tissue-specific architectures. Here we present PathoGen, a diffusion-based generative model enabling controllable, high-fidelity lesion inpainting into benign histopathology images. We validate PathoGen across four datasets representing kidney, skin, breast, and prostate pathology. Quantitative assessment confirms PathoGen outperforms state-of-the-art baselines in image fidelity and distributional similarity. Evaluation by six expert pathologists revealed that synthetic images by PathoGen were only marginally distinguished from real tissue image slightly above chance (57.75% accuracy), demonstrating strong perceptual realism of PathoGen-generated lesions. PathoGen achieved the highest win rate (35.4%) when pathologists ranked generation quality against all baselines. Crucially, augmenting training sets with PathoGen-synthesized lesions improves segmentation Dice scores by up to 0.18 compared to traditional augmentations, with maximum benefit in data-scarce regimes. By simultaneously generating realistic morphology and pixel-level annotations, PathoGen effectively addresses both data scarcity and annotation cost, two critical bottlenecks in computational pathology development. △ Less

Submitted 1 July, 2026; v1 submitted 12 January, 2026; originally announced January 2026.

Comments: 19 pages, 5 figures, 1 Table

MHR: Momentum Human Rig

Authors: Aaron Ferguson, Ahmed A. A. Osman, Berta Bescos, Carsten Stoll, Chris Twigg, Christoph Lassner, David Otte, Eric Vignola, Fabian Prada, Federica Bogo, Igor Santesteban, Javier Romero, Jenna Zarate, Jeongseok Lee, Jinhyung Park, Jinlong Yang, John Doublestein, Kishore Venkateshan, Kris Kitani, Ladislav Kavan, Marco Dal Farra, Matthew Hu, Matthew Cioffi, Michael Fabris, Michael Ranieri , et al. (22 additional authors not shown)

Abstract: We present MHR, a parametric human body model that combines the decoupled skeleton/shape paradigm of ATLAS with a flexible, modern rig and pose corrective system inspired by the Momentum library. Our model enables expressive, anatomically plausible human animation, supporting non-linear pose correctives, and is designed for robust integration in AR/VR and graphics pipelines. We present MHR, a parametric human body model that combines the decoupled skeleton/shape paradigm of ATLAS with a flexible, modern rig and pose corrective system inspired by the Momentum library. Our model enables expressive, anatomically plausible human animation, supporting non-linear pose correctives, and is designed for robust integration in AR/VR and graphics pipelines. △ Less

Submitted 24 November, 2025; v1 submitted 19 November, 2025; originally announced November 2025.

The Future of Artificial Intelligence and the Mathematical and Physical Sciences (AI+MPS)

Authors: Andrew Ferguson, Marisa LaFleur, Lars Ruthotto, Jesse Thaler, Yuan-Sen Ting, Pratyush Tiwary, Soledad Villar, E. Paulo Alves, Jeremy Avigad, Simon Billinge, Camille Bilodeau, Keith Brown, Emmanuel Candes, Arghya Chattopadhyay, Bingqing Cheng, Jonathan Clausen, Connor Coley, Andrew Connolly, Fred Daum, Sijia Dong, Chrisy Xiyu Du, Cora Dvorkin, Cristiano Fanelli, Eric B. Ford, Luis Manuel Frutos , et al. (75 additional authors not shown)

Abstract: This community paper developed out of the NSF Workshop on the Future of Artificial Intelligence (AI) and the Mathematical and Physics Sciences (MPS), which was held in March 2025 with the goal of understanding how the MPS domains (Astronomy, Chemistry, Materials Research, Mathematical Sciences, and Physics) can best capitalize on, and contribute to, the future of AI. We present here a summary and… ▽ More This community paper developed out of the NSF Workshop on the Future of Artificial Intelligence (AI) and the Mathematical and Physics Sciences (MPS), which was held in March 2025 with the goal of understanding how the MPS domains (Astronomy, Chemistry, Materials Research, Mathematical Sciences, and Physics) can best capitalize on, and contribute to, the future of AI. We present here a summary and snapshot of the MPS community's perspective, as of Spring/Summer 2025, in a rapidly developing field. The link between AI and MPS is becoming increasingly inextricable; now is a crucial moment to strengthen the link between AI and Science by pursuing a strategy that proactively and thoughtfully leverages the potential of AI for scientific discovery and optimizes opportunities to impact the development of AI by applying concepts from fundamental science. To achieve this, we propose activities and strategic priorities that: (1) enable AI+MPS research in both directions; (2) build up an interdisciplinary community of AI+MPS researchers; and (3) foster education and workforce development in AI for MPS researchers and students. We conclude with a summary of suggested priorities for funding agencies, educational institutions, and individual researchers to help position the MPS community to be a leader in, and take full advantage of, the transformative potential of AI+MPS. △ Less

Submitted 15 March, 2026; v1 submitted 2 September, 2025; originally announced September 2025.

Comments: Community Paper from the NSF Future of AI+MPS Workshop, Cambridge, Massachusetts, March 24-26, 2025, supported by NSF Award Number 2512945; v2: minor clarifications; v3: approximate version to appear in MLST

Campus5G: A Campus Scale Private 5G Open RAN Testbed

Authors: Andrew E. Ferguson, Ujjwal Pawar, Tianxin Wang, Mahesh K. Marina

Abstract: Mobile networks are embracing disaggregation, reflected by the industry trend towards Open RAN. Private 5G networks are viewed as particularly suitable contenders as early adopters of Open RAN, owing to their setting, high degree of control, and opportunity for innovation they present. Motivated by this, we have recently deployed Campus5G, the first of its kind campus-wide, O-RAN-compliant private… ▽ More Mobile networks are embracing disaggregation, reflected by the industry trend towards Open RAN. Private 5G networks are viewed as particularly suitable contenders as early adopters of Open RAN, owing to their setting, high degree of control, and opportunity for innovation they present. Motivated by this, we have recently deployed Campus5G, the first of its kind campus-wide, O-RAN-compliant private 5G testbed across the central campus of the University of Edinburgh. We present in detail our process developing the testbed, from planning, to architecting, to deployment, and measuring the testbed performance. We then discuss the lessons learned from building the testbed, and highlight some research opportunities that emerged from our deployment experience. △ Less

Submitted 22 December, 2025; v1 submitted 30 June, 2025; originally announced June 2025.

Comments: To appear in ACM SIGCOMM Computer Communication Review (CCR), July 2025

ACM Class: C.2.1

Exploiting Unstructured Sparsity in Fully Homomorphic Encrypted DNNs

Authors: Aidan Ferguson, Perry Gibson, Lara D'Agata, Parker McLeod, Ferhat Yaman, Amitabh Das, Ian Colbert, José Cano

Abstract: The deployment of deep neural networks (DNNs) in privacy-sensitive environments is constrained by computational overheads in fully homomorphic encryption (FHE). This paper explores unstructured sparsity in FHE matrix multiplication schemes as a means of reducing this burden while maintaining model accuracy requirements. We demonstrate that sparsity can be exploited in arbitrary matrix multiplicati… ▽ More The deployment of deep neural networks (DNNs) in privacy-sensitive environments is constrained by computational overheads in fully homomorphic encryption (FHE). This paper explores unstructured sparsity in FHE matrix multiplication schemes as a means of reducing this burden while maintaining model accuracy requirements. We demonstrate that sparsity can be exploited in arbitrary matrix multiplication, providing runtime benefits compared to a baseline naive algorithm at all sparsity levels. This is a notable departure from the plaintext domain, where there is a trade-off between sparsity and the overhead of the sparse multiplication algorithm. In addition, we propose three sparse multiplication schemes in FHE based on common plaintext sparse encodings. We demonstrate the performance gain is scheme-invariant; however, some sparse schemes vastly reduce the memory storage requirements of the encrypted matrix at high sparsity values. Our proposed sparse schemes yield an average performance gain of 2.5x at 50% unstructured sparsity, with our multi-threading scheme providing a 32.5x performance increase over the equivalent single-threaded sparse computation when utilizing 64 cores. △ Less

Submitted 3 April, 2025; v1 submitted 12 March, 2025; originally announced March 2025.

Comments: Accepted to 5th Workshop on Machine Learning and Systems (EuroMLSys) co-located with EuroSys '25

Scaling Laws for Galaxy Images

Authors: Mike Walmsley, Micah Bowles, Anna M. M. Scaife, Jason Shingirai Makechemu, Alexander J. Gordon, Annette M. N. Ferguson, Robert G. Mann, James Pearson, Jürgen J. Popp, Jo Bovy, Josh Speagle, Hugh Dickinson, Lucy Fortson, Tobias Géron, Sandor Kruk, Chris J. Lintott, Kameswara Mantha, Devina Mohan, David O'Ryan, Inigo V. Slijepevic

Abstract: We present the first systematic investigation of supervised scaling laws outside of an ImageNet-like context - on images of galaxies. We use 840k galaxy images and over 100M annotations by Galaxy Zoo volunteers, comparable in scale to Imagenet-1K. We find that adding annotated galaxy images provides a power law improvement in performance across all architectures and all tasks, while adding trainab… ▽ More We present the first systematic investigation of supervised scaling laws outside of an ImageNet-like context - on images of galaxies. We use 840k galaxy images and over 100M annotations by Galaxy Zoo volunteers, comparable in scale to Imagenet-1K. We find that adding annotated galaxy images provides a power law improvement in performance across all architectures and all tasks, while adding trainable parameters is effective only for some (typically more subjectively challenging) tasks. We then compare the downstream performance of finetuned models pretrained on either ImageNet-12k alone vs. additionally pretrained on our galaxy images. We achieve an average relative error rate reduction of 31% across 5 downstream tasks of scientific interest. Our finetuned models are more label-efficient and, unlike their ImageNet-12k-pretrained equivalents, often achieve linear transfer performance equal to that of end-to-end finetuning. We find relatively modest additional downstream benefits from scaling model size, implying that scaling alone is not sufficient to address our domain gap, and suggest that practitioners with qualitatively different images might benefit more from in-domain adaption followed by targeted downstream labelling. △ Less

Submitted 3 April, 2024; originally announced April 2024.

Comments: 10+6 pages, 12 figures. Appendix C2 based on arxiv:2206.11927. Code, demos, documentation at https://github.com/mwalmsley/zoobot

A Multifaceted Look at Starlink Performance

Authors: Nitinder Mohan, Andrew Ferguson, Hendrik Cech, Prakita Rayyan Renatin, Rohan Bose, Mahesh Marina, Jörg Ott

Abstract: In recent years, Low-Earth Orbit (LEO) mega-constellations have emerged as a promising network technology and have ushered in a new era for democratizing Internet access. The Starlink network from SpaceX stands out as the only consumer-facing LEO network with over 2M+ customers and more than 4000 operational satellites. In this paper, we conduct the first-of-its-kind extensive multi-faceted analys… ▽ More In recent years, Low-Earth Orbit (LEO) mega-constellations have emerged as a promising network technology and have ushered in a new era for democratizing Internet access. The Starlink network from SpaceX stands out as the only consumer-facing LEO network with over 2M+ customers and more than 4000 operational satellites. In this paper, we conduct the first-of-its-kind extensive multi-faceted analysis of Starlink network performance leveraging several measurement sources. First, based on 19.2M crowdsourced M-Lab speed test measurements from 34 countries since 2021, we analyze Starlink global performance relative to terrestrial cellular networks. Second, we examine Starlink's ability to support real-time web-based latency and bandwidth-critical applications by analyzing the performance of (i) Zoom video conferencing, and (ii) Luna cloud gaming, comparing it to 5G and terrestrial fiber. Third, we orchestrate targeted measurements from Starlink-enabled RIPE Atlas probes to shed light on the last-mile Starlink access and other factors affecting its performance globally. Finally, we conduct controlled experiments from Starlink dishes in two countries and analyze the impact of globally synchronized "15-second reconfiguration intervals" of the links that cause substantial latency and throughput variations. Our unique analysis provides revealing insights on global Starlink functionality and paints the most comprehensive picture of the LEO network's operation to date. △ Less

Submitted 22 February, 2024; v1 submitted 13 October, 2023; originally announced October 2023.

Comments: Accepted in ACM Web Conference 2024 (WWW 24)

Journal ref: In Proceedings of ACM Web Conference 2024 (WWW 24)

DiAMoNDBack: Diffusion-denoising Autoregressive Model for Non-Deterministic Backmapping of Cα Protein Traces

Authors: Michael S. Jones, Kirill Shmilovich, Andrew L. Ferguson

Abstract: Coarse-grained molecular models of proteins permit access to length and time scales unattainable by all-atom models and the simulation of processes that occur on long-time scales such as aggregation and folding. The reduced resolution realizes computational accelerations but an atomistic representation can be vital for a complete understanding of mechanistic details. Backmapping is the process of… ▽ More Coarse-grained molecular models of proteins permit access to length and time scales unattainable by all-atom models and the simulation of processes that occur on long-time scales such as aggregation and folding. The reduced resolution realizes computational accelerations but an atomistic representation can be vital for a complete understanding of mechanistic details. Backmapping is the process of restoring all-atom resolution to coarse-grained molecular models. In this work, we report DiAMoNDBack (Diffusion-denoising Autoregressive Model for Non-Deterministic Backmapping) as an autoregressive denoising diffusion probability model to restore all-atom details to coarse-grained protein representations retaining only Cα coordinates. The autoregressive generation process proceeds from the protein N-terminus to C-terminus in a residue-by-residue fashion conditioned on the Cα trace and previously backmapped backbone and side chain atoms within the local neighborhood. The local and autoregressive nature of our model makes it transferable between proteins. The stochastic nature of the denoising diffusion process means that the model generates a realistic ensemble of backbone and side chain all-atom configurations consistent with the coarse-grained Cα trace. We train DiAMoNDBack over 65k+ structures from Protein Data Bank (PDB) and validate it in applications to a hold-out PDB test set, intrinsically-disordered protein structures from the Protein Ensemble Database (PED), molecular dynamics simulations of fast-folding mini-proteins from DE Shaw Research, and coarse-grained simulation data. We achieve state-of-the-art reconstruction performance in terms of correct bond formation, avoidance of side chain clashes, and diversity of the generated side chain configurational states. We make DiAMoNDBack model publicly available as a free and open source Python package. △ Less

Submitted 23 July, 2023; originally announced July 2023.

GANs and Closures: Micro-Macro Consistency in Multiscale Modeling

Authors: Ellis R. Crabtree, Juan M. Bello-Rivas, Andrew L. Ferguson, Ioannis G. Kevrekidis

Abstract: Sampling the phase space of molecular systems -- and, more generally, of complex systems effectively modeled by stochastic differential equations -- is a crucial modeling step in many fields, from protein folding to materials discovery. These problems are often multiscale in nature: they can be described in terms of low-dimensional effective free energy surfaces parametrized by a small number of "… ▽ More Sampling the phase space of molecular systems -- and, more generally, of complex systems effectively modeled by stochastic differential equations -- is a crucial modeling step in many fields, from protein folding to materials discovery. These problems are often multiscale in nature: they can be described in terms of low-dimensional effective free energy surfaces parametrized by a small number of "slow" reaction coordinates; the remaining "fast" degrees of freedom populate an equilibrium measure on the reaction coordinate values. Sampling procedures for such problems are used to estimate effective free energy differences as well as ensemble averages with respect to the conditional equilibrium distributions; these latter averages lead to closures for effective reduced dynamic models. Over the years, enhanced sampling techniques coupled with molecular simulation have been developed. An intriguing analogy arises with the field of Machine Learning (ML), where Generative Adversarial Networks can produce high dimensional samples from low dimensional probability distributions. This sample generation returns plausible high dimensional space realizations of a model state, from information about its low-dimensional representation. In this work, we present an approach that couples physics-based simulations and biasing methods for sampling conditional distributions with ML-based conditional generative adversarial networks for the same task. The "coarse descriptors" on which we condition the fine scale realizations can either be known a priori, or learned through nonlinear dimensionality reduction. We suggest that this may bring out the best features of both approaches: we demonstrate that a framework that couples cGANs with physics-based enhanced sampling techniques can improve multiscale SDE dynamical systems sampling, and even shows promise for systems of increasing complexity. △ Less

Submitted 9 December, 2023; v1 submitted 22 August, 2022; originally announced August 2022.

Comments: 26 pages, 14 figures, 3 tables

MSC Class: 82C32 (Primary) 37M05; 60H10; 68T07; 82-08 (Secondary)

Gröbner bases and critical values: The asymptotic combinatorics of determinantal systems

Authors: Alin Bostan, Jérémy Berthomieu, Andrew Ferguson, Mohab Safey El Din

Abstract: We consider ideals involving the maximal minors of a polynomial matrix. For example, those arising in the computation of the critical values of a polynomial restricted to a variety for polynomial optimisation. Gröbner bases are a classical tool for solving polynomial systems. For practical computations, this consists of two stages. First, a Gröbner basis is computed with respect to a DRL (degree r… ▽ More We consider ideals involving the maximal minors of a polynomial matrix. For example, those arising in the computation of the critical values of a polynomial restricted to a variety for polynomial optimisation. Gröbner bases are a classical tool for solving polynomial systems. For practical computations, this consists of two stages. First, a Gröbner basis is computed with respect to a DRL (degree reverse lexicographic) ordering. Then, a change of ordering algorithm, such as \textsf{Sparse-FGLM}, designed by Faugère and Mou, is used to find a Gröbner basis of the same ideal but with respect to a lexicographic ordering. The complexity of this latter step, in terms of arithmetic operations, is $O(mD^2)$, where $D$ is the degree of the ideal and $m$ is the number of non-trivial columns of a certain $D \times D$ matrix. While asymptotic estimates are known for $m$ for generic polynomial systems, thus far, the complexity of \textsf{Sparse-FGLM} was unknown for determinantal systems. By assuming Fröberg's conjecture we expand the work of Moreno-Socías by detailing the structure of the DRL staircase in the determinantal setting. Then we study the asymptotics of the quantity $m$ by relating it to the coefficients of these Hilbert series. Consequently, we arrive at a new bound on the complexity of the \textsf{Sparse-FGLM} algorithm for generic determinantal systems and for generic critical point systems. We consider the ideal in the polynomial ring $\mathbb{K}[x_1, \dots, x_n]$, where $\mathbb{K}$ is some infinite field, generated by $p$ generic polynomials of degree $d$ and the maximal minors of a $p \times (n-1)$ polynomial matrix with generic entries of degree $d-1$. Then for the case $d=2$ and for $n \gg p$ we give an exact formula for $m$ in terms of $n$ and $p$. Moreover, for $d \geq 3$, we give an asymptotic formula, as $n \to \infty$, for $m$ in terms of $n,p$ and $d$. △ Less

Submitted 18 March, 2022; originally announced March 2022.

Unsupervised Learning for Target Tracking and Background Subtraction in Satellite Imagery

Authors: Jonathan S. Kent, Charles C. Wamsley, Davin Flateau, Amber Ferguson

Abstract: This paper describes an unsupervised machine learning methodology capable of target tracking and background suppression via a novel dual-model approach. ``Jekyll`` produces a video bit-mask describing an estimate of the locations of moving objects, and ``Hyde`` outputs a pseudo-background frame to subtract from the original input image sequence. These models were trained with a custom-modified ver… ▽ More This paper describes an unsupervised machine learning methodology capable of target tracking and background suppression via a novel dual-model approach. ``Jekyll`` produces a video bit-mask describing an estimate of the locations of moving objects, and ``Hyde`` outputs a pseudo-background frame to subtract from the original input image sequence. These models were trained with a custom-modified version of Cross Entropy Loss. Simulated data were used to compare the performance of Jekyll and Hyde against a more traditional supervised Machine Learning approach. The results from these comparisons show that the unsupervised methods developed are competitive in output quality with supervised techniques, without the associated cost of acquiring labeled training data. △ Less

Submitted 13 August, 2021; originally announced September 2021.

Comments: 10 pages

ACM Class: I.4.6

Journal ref: Conference: SPIE 2021, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications III. Volume: 11746. Pages: 117460H. Year: 2021. Organization: International Society for Optics and Photonics

Towards an Extrinsic, CG-XFEM Approach Based on Hierarchical Enrichments for Modeling Progressive Fracture

Authors: M. Keith Ballard, Roman Amici, Varun Shankar, Lauren A. Ferguson, Michael Braginsky, Robert M. Kirby

Abstract: We propose an extrinsic, continuous-Galerkin (CG), extended finite element method (XFEM) that generalizes the work of Hansbo and Hansbo to allow multiple Heaviside enrichments within a single element in a hierarchical manner. This approach enables complex, evolving XFEM surfaces in 3D that cannot be captured using existing CG-XFEM approaches. We describe an implementation of the method for 3D stat… ▽ More We propose an extrinsic, continuous-Galerkin (CG), extended finite element method (XFEM) that generalizes the work of Hansbo and Hansbo to allow multiple Heaviside enrichments within a single element in a hierarchical manner. This approach enables complex, evolving XFEM surfaces in 3D that cannot be captured using existing CG-XFEM approaches. We describe an implementation of the method for 3D static elasticity with linearized strain for modeling open cracks as a salient step towards modeling progressive fracture. The implementation includes a description of the finite element model, hybrid implicit/explicit representation of enrichments, numerical integration method, and novel degree-of-freedom (DoF) enumeration algorithm. This algorithm supports an arbitrary number of enrichments within an element, while simultaneously maintaining a CG solution across elements. Additionally, our approach easily allows an implementation suitable for distributed computing systems. Enabled by the DoF enumeration algorithm, the proposed method lays the groundwork for a computational tool that efficiently models progressive fracture. To facilitate a discussion of the complex enrichment hierarchies, we develop enrichment diagrams to succinctly describe and visualize the relationships between the enrichments (and the fields they create) within an element. This also provides a unified language for discussing extrinsic XFEM methods in the literature. We compare several methods, relying on the enrichment diagrams to highlight their nuanced differences. △ Less

Submitted 29 April, 2021; originally announced April 2021.

On the computation of asymptotic critical values of polynomial maps and applications

Authors: Jérémy Berthomieu, Andrew Ferguson, Mohab Safey El Din

Abstract: Let $\mathbf{f} = \left(f_1, \dots, f_p\right) $ be a polynomial tuple in $\mathbb{Q}[z_1, \dots, z_n]$ and let $d = \max_{1 \leq i \leq p} °f_i$. We consider the problem of computing the set of asymptotic critical values of the polynomial mapping, with the assumption that this mapping is dominant, $\mathbf{f}: z \in \mathbb{K}^n \to (f\_1(z), \dots, f\_p(z)) \in \mathbb{K}^p$ where $\mathbb{K}$ i… ▽ More Let $\mathbf{f} = \left(f_1, \dots, f_p\right) $ be a polynomial tuple in $\mathbb{Q}[z_1, \dots, z_n]$ and let $d = \max_{1 \leq i \leq p} °f_i$. We consider the problem of computing the set of asymptotic critical values of the polynomial mapping, with the assumption that this mapping is dominant, $\mathbf{f}: z \in \mathbb{K}^n \to (f\_1(z), \dots, f\_p(z)) \in \mathbb{K}^p$ where $\mathbb{K}$ is either $\mathbb{R}$ or $\mathbb{C}$. This is the set of values $c$ in the target space of $\mathbf{f}$ such that there exists a sequence of points $(\mathbf{x}_i)_{i\in \mathbb{N}}$ for which $\mathbf{f}(\mathbf{x}_i)$ tends to $c$ and $\|\mathbf{x}_i\| κ{\rm d} \mathbf{f}(\mathbf{x}_i))$ tends to $0$ when $i$ tends to infinity where ${\rm d} \mathbf{f}$ is the differential of $\mathbf{f}$ and $κ$ is a function measuring the distance of a linear operator to the set of singular linear operators from $\mathbb{K}^n$ to $\mathbb{K}^p$. Computing the union of the classical and asymptotic critical values allows one to put into practice generalisations of Ehresmann's fibration theorem. This leads to natural and efficient applications in polynomial optimisation and computational real algebraic geometry. Going back to previous works by Kurdyka, Orro and Simon, we design new algorithms to compute asymptotic critical values. Through randomisation, we introduce new geometric characterisations of asymptotic critical values. This allows us to dramatically reduce the complexity of computing such values to a cost that is essentially $O(d^{2n(p+1)})$ arithmetic operations in $\mathbb{Q}$. We also obtain tighter degree bounds on a hypersurface containing the asymptotic critical values, showing that the degree is at most $p^{n-p+1}(d-1)^{n-p}(d+1)^{p}$. Next, we show how to apply these algorithms to unconstrained polynomial optimisation problems and the problem of computing sample points per connected component of a semi-algebraic set defined by a single inequality/inequation. We report on the practical capabilities of our implementation of this algorithm. It shows how the practical efficiency surpasses the current state-of-the-art algorithms for computing asymptotic critical values by tackling examples that were previously out of reach. △ Less

Submitted 2 April, 2021; originally announced April 2021.

Tip of the Tongue Known-Item Retrieval: A Case Study in Movie Identification

Authors: Jaime Arguello, Adam Ferguson, Emery Fine, Bhaskar Mitra, Hamed Zamani, Fernando Diaz

Abstract: While current information retrieval systems are effective for known-item retrieval where the searcher provides a precise name or identifier for the item being sought, systems tend to be much less effective for cases where the searcher is unable to express a precise name or identifier. We refer to this as tip of the tongue (TOT) known-item retrieval, named after the cognitive state of not being abl… ▽ More While current information retrieval systems are effective for known-item retrieval where the searcher provides a precise name or identifier for the item being sought, systems tend to be much less effective for cases where the searcher is unable to express a precise name or identifier. We refer to this as tip of the tongue (TOT) known-item retrieval, named after the cognitive state of not being able to retrieve an item from memory. Using movie search as a case study, we explore the characteristics of questions posed by searchers in TOT states in a community question answering website. We analyze how searchers express their information needs during TOT states in the movie domain. Specifically, what information do searchers remember about the item being sought and how do they convey this information? Our results suggest that searchers use a combination of information about: (1) the content of the item sought, (2) the context in which they previously engaged with the item, and (3) previous attempts to find the item using other resources (e.g., search engines). Additionally, searchers convey information by sometimes expressing uncertainty (i.e., hedging), opinions, emotions, and by performing relative (vs. absolute) comparisons with attributes of the item. As a result of our analysis, we believe that searchers in TOT states may require specialized query understanding methods or document representations. Finally, our preliminary retrieval experiments show the impact of each information type presented in information requests on retrieval performance. △ Less

Submitted 18 January, 2021; originally announced January 2021.

Mixture Model Framework for Traumatic Brain Injury Prognosis Using Heterogeneous Clinical and Outcome Data

Authors: Alan D. Kaplan, Qi Cheng, K. Aditya Mohan, Lindsay D. Nelson, Sonia Jain, Harvey Levin, Abel Torres-Espin, Austin Chou, J. Russell Huie, Adam R. Ferguson, Michael McCrea, Joseph Giacino, Shivshankar Sundaram, Amy J. Markowitz, Geoffrey T. Manley

Abstract: Prognoses of Traumatic Brain Injury (TBI) outcomes are neither easily nor accurately determined from clinical indicators. This is due in part to the heterogeneity of damage inflicted to the brain, ultimately resulting in diverse and complex outcomes. Using a data-driven approach on many distinct data elements may be necessary to describe this large set of outcomes and thereby robustly depict the n… ▽ More Prognoses of Traumatic Brain Injury (TBI) outcomes are neither easily nor accurately determined from clinical indicators. This is due in part to the heterogeneity of damage inflicted to the brain, ultimately resulting in diverse and complex outcomes. Using a data-driven approach on many distinct data elements may be necessary to describe this large set of outcomes and thereby robustly depict the nuanced differences among TBI patients' recovery. In this work, we develop a method for modeling large heterogeneous data types relevant to TBI. Our approach is geared toward the probabilistic representation of mixed continuous and discrete variables with missing values. The model is trained on a dataset encompassing a variety of data types, including demographics, blood-based biomarkers, and imaging findings. In addition, it includes a set of clinical outcome assessments at 3, 6, and 12 months post-injury. The model is used to stratify patients into distinct groups in an unsupervised learning setting. We use the model to infer outcomes using input data, and show that the collection of input data reduces uncertainty of outcomes over a baseline approach. In addition, we quantify the performance of a likelihood scoring technique that can be used to self-evaluate the extrapolation risk of prognosis on unseen patients. △ Less

Submitted 20 July, 2021; v1 submitted 22 December, 2020; originally announced December 2020.

Comments: 12 pages, 5 figures

Discovery of Self-Assembling $π$-Conjugated Peptides by Active Learning-Directed Coarse-Grained Molecular Simulation

Authors: Kirill Shmilovich, Rachael A. Mansbach, Hythem Sidky, Olivia E. Dunne, Sayak Subhra Panda, John D. Tovar, Andrew L. Ferguson

Abstract: Electronically-active organic molecules have demonstrated great promise as novel soft materials for energy harvesting and transport. Self-assembled nanoaggregates formed from $π$-conjugated oligopeptides composed of an aromatic core flanked by oligopeptide wings offer emergent optoelectronic properties within a water soluble and biocompatible substrate. Nanoaggregate properties can be controlled b… ▽ More Electronically-active organic molecules have demonstrated great promise as novel soft materials for energy harvesting and transport. Self-assembled nanoaggregates formed from $π$-conjugated oligopeptides composed of an aromatic core flanked by oligopeptide wings offer emergent optoelectronic properties within a water soluble and biocompatible substrate. Nanoaggregate properties can be controlled by tuning core chemistry and peptide composition, but the sequence-structure-function relations remain poorly characterized. In this work, we employ coarse-grained molecular dynamics simulations within an active learning protocol employing deep representational learning and Bayesian optimization to efficiently identify molecules capable of assembling pseudo-1D nanoaggregates with good stacking of the electronically-active $π$-cores. We consider the DXXX-OPV3-XXXD oligopeptide family, where D is an Asp residue and OPV3 is an oligophenylene vinylene oligomer (1,4-distyrylbenzene), to identify the top performing XXX tripeptides within all 20$^3$ = 8,000 possible sequences. By direct simulation of only 2.3% of this space, we identify molecules predicted to exhibit superior assembly relative to those reported in prior work. Spectral clustering of the top candidates reveals new design rules governing assembly. This work establishes new understanding of DXXX-OPV3-XXXD assembly, identifies promising new candidates for experimental testing, and presents a computational design platform that can be generically extended to other peptide-based and peptide-like systems. △ Less

Submitted 26 January, 2020; originally announced February 2020.

Capabilities and Limitations of Time-lagged Autoencoders for Slow Mode Discovery in Dynamical Systems

Authors: Wei Chen, Hythem Sidky, Andrew L. Ferguson

Abstract: Time-lagged autoencoders (TAEs) have been proposed as a deep learning regression-based approach to the discovery of slow modes in dynamical systems. However, a rigorous analysis of nonlinear TAEs remains lacking. In this work, we discuss the capabilities and limitations of TAEs through both theoretical and numerical analyses. Theoretically, we derive bounds for nonlinear TAE performance in slow mo… ▽ More Time-lagged autoencoders (TAEs) have been proposed as a deep learning regression-based approach to the discovery of slow modes in dynamical systems. However, a rigorous analysis of nonlinear TAEs remains lacking. In this work, we discuss the capabilities and limitations of TAEs through both theoretical and numerical analyses. Theoretically, we derive bounds for nonlinear TAE performance in slow mode discovery and show that in general TAEs learn a mixture of slow and maximum variance modes. Numerically, we illustrate cases where TAEs can and cannot correctly identify the leading slowest mode in two example systems: a 2D "Washington beltway" potential and the alanine dipeptide molecule in explicit water. We also compare the TAE results with those obtained using state-free reversible VAMPnets (SRVs) as a variational-based neural network approach for slow modes discovery, and show that SRVs can correctly discover slow modes where TAEs fail. △ Less

Submitted 1 June, 2019; originally announced June 2019.

Nonlinear Discovery of Slow Molecular Modes using State-Free Reversible VAMPnets

Authors: Wei Chen, Hythem Sidky, Andrew L Ferguson

Abstract: The success of enhanced sampling molecular simulations that accelerate along collective variables (CVs) is predicated on the availability of variables coincident with the slow collective motions governing the long-time conformational dynamics of a system. It is challenging to intuit these slow CVs for all but the simplest molecular systems, and their data-driven discovery directly from molecular s… ▽ More The success of enhanced sampling molecular simulations that accelerate along collective variables (CVs) is predicated on the availability of variables coincident with the slow collective motions governing the long-time conformational dynamics of a system. It is challenging to intuit these slow CVs for all but the simplest molecular systems, and their data-driven discovery directly from molecular simulation trajectories has been a central focus of the molecular simulation community to both unveil the important physical mechanisms and to drive enhanced sampling. In this work, we introduce state-free reversible VAMPnets (SRV) as a deep learning architecture that learns nonlinear CV approximants to the leading slow eigenfunctions of the spectral decomposition of the transfer operator that evolves equilibrium-scaled probability distributions through time. Orthogonality of the learned CVs is naturally imposed within network training without added regularization. The CVs are inherently explicit and differentiable functions of the input coordinates making them well-suited to use in enhanced sampling calculations. We demonstrate the utility of SRVs in capturing parsimonious nonlinear representations of complex system dynamics in applications to 1D and 2D toy systems where the true eigenfunctions are exactly calculable and to molecular dynamics simulations of alanine dipeptide and the WW domain protein. △ Less

Submitted 1 June, 2019; v1 submitted 8 February, 2019; originally announced February 2019.