Skip to main content
arXiv is now an independent nonprofit! Learn more

Showing 1–17 of 17 results for author: Şahin, B

Searching in archive cs. Search in all archives.
.
  1. arXiv:2608.15966  [pdf, ps, other

    cs.LG math.OC

    A Banach-Space Theory of Markovian Halpern Iteration for Non-Expansive Maps

    Authors: Ege C. Kaya, Arda Fazla, M. Berk Sahin, Abolfazl Hashemi

    Abstract: We study stochastic approximation of fixed points of a non-expansive operator when the oracle samples originate from a continuing Markovian trajectory. A direct block-minibatch implementation of Halpern iteration attains an expected last-iterate residual of order $O(\log N/N)$, but accrues a substantive complexity of $\tilde O(ε^{-5})$ Markovian samples. We therefore introduce a variance-reduced M… ▽ More

    Submitted 16 August, 2026; originally announced August 2026.

    Comments: 34 pages, 1 figure

  2. arXiv:2606.16257  [pdf, ps, other

    cs.LG cs.AI

    Variance Reduction for Non-Log-Concave Sampling with Applications to Inverse Problems

    Authors: M. Berk Sahin, Ahmet Ege Tanriverdi, Behzad Sharif, Abolfazl Hashemi

    Abstract: Sampling from high-dimensional, non-log-concave distributions with unnormalized densities is a fundamental challenge in machine learning, particularly when the exact gradient of the potential is unavailable and must be approximated via stochastic gradients that exhibit high variance under a fixed budget of gradient computations per iteration. Although variance reduction techniques such as SGD with… ▽ More

    Submitted 15 June, 2026; originally announced June 2026.

    Comments: Accepted to Uncertainty in Artificial Intelligence (UAI) 2026

  3. arXiv:2605.30573  [pdf, ps, other

    cs.LG

    Zeroth-Order Non-Log-Concave Sampling with Variance Reduction and Applications to Inverse Problems

    Authors: M. Berk Sahin, Behzad Sharif, Abolfazl Hashemi

    Abstract: Sampling from high-dimensional, non-log-concave distributions with unnormalized densities remains a fundamental challenge in machine learning, particularly in black-box settings where gradient information is inaccessible or computationally prohibitive. While Langevin dynamics provides a principled framework for sampling when gradients are accessible, its extension to the black-box settings suffers… ▽ More

    Submitted 28 May, 2026; originally announced May 2026.

    Comments: Accepted to ICML 2026

  4. arXiv:2605.15388  [pdf, ps, other

    cs.LG

    Unified High-Probability Analysis of Stochastic Variance-Reduced Estimation

    Authors: Zhankun Luo, Antesh Upadhyay, M. Berk Sahin, Sang Bin Moon, Anuran Makur, Abolfazl Hashemi

    Abstract: Stochastic estimators are fundamental to large-scale optimization, where population quantities must be inferred from noisy oracle observations. Although influential methods such as momentum, SPIDER, STORM, and PAGE have been highly successful, their analyses are largely estimator-specific and expectation-based, obscuring the structural tradeoffs that determine reliability. In this paper, we develo… ▽ More

    Submitted 14 May, 2026; originally announced May 2026.

  5. arXiv:2605.07142  [pdf, ps, other

    cs.CV

    AGA3DNet: Anatomy-Guided Gaussian Priors with Multi-view xLSTM for 3D Brain MRI Subtype Classification

    Authors: Peiyu Duan, Xueqi Guo, Sepehr Farhand, Mehmet Berk Sahin, Xinyuan Zheng, James S. Duncan, Gerardo Hermosillo Valadez, Yoshihisa Shinagawa

    Abstract: Accurate 3D brain MRI subtype classification benefits from both localized anatomical cues and long-range contextual reasoning. We present AGA3DNet, a report-grounded framework that incorporates brief anatomical phrases extracted from radiology reports as a soft anatomical prior channel and fuses it with a lightweight 3D CNN and multi-view xLSTM aggregation. Specifically, extracted anatomical phras… ▽ More

    Submitted 7 May, 2026; originally announced May 2026.

    Comments: CVPR CV4CLINIC 2026

  6. arXiv:2605.05618  [pdf, ps, other

    cs.DS cs.CC cs.DM math.CO math.PR

    Algorithmic Phase Transition for Large Independent Sets in Dense Hypergraphs

    Authors: Abhishek Dhawan, Nhi U. Dinh, Eren C. Kızıldağ, Neeladri Maitra, Bayram A. Şahin

    Abstract: We study the algorithmic tractability of finding large independent sets in dense random hypergraphs. In the sparse regime, much of the natural algorithms can be formulated within either the local or the low-degree polynomial (LDP) framework, and a rich literature has subsequently identified nearly sharp algorithmic thresholds within these classes by exploiting their stability. In the dense setting… ▽ More

    Submitted 6 May, 2026; originally announced May 2026.

    Comments: 38 pages plus references; abstract shortened due to arxiv restrictions

  7. arXiv:2605.01185  [pdf, ps, other

    cs.CV

    Phase-map synthesis from magnitude-only MR images using conditional score-based diffusion models with application in training of accelerated MRI reconstruction models

    Authors: M. Berk Sahin, Dilek Yalcinkaya, Abolfazl Hashemi, Behzad Sharif

    Abstract: Accelerated magnetic resonance imaging (MRI) enabled by the training of deep learning (DL)-based image recon. models requires large and diverse raw k-space datasets. In most clinical MRI applications, due to storage and patient privacy concerns, raw k-space data is discarded and magnitude-only images are the only component saved. Consequently, a large portion of the DL-based MRI recon. literature… ▽ More

    Submitted 1 May, 2026; originally announced May 2026.

  8. arXiv:2603.22155  [pdf, ps, other

    cs.LG math.OC

    RAMPAGE: RAndomized Mid-Point for debiAsed Gradient Extrapolation

    Authors: Zhankun Luo, M. Berk Sahin, Antesh Upadhyay, Behzad Sharif, Abolfazl Hashemi

    Abstract: A celebrated method for Variational Inequalities (VIs) is Extragradient (EG), which can be viewed as a standard discrete-time integration scheme. With this view in mind, in this paper we show that EG may suffer from discretization bias when applied to non-linear vector fields, conservative or otherwise. To resolve this discretization shortcoming, we introduce RAndomized Mid-Point for debiAsed Grad… ▽ More

    Submitted 7 May, 2026; v1 submitted 23 March, 2026; originally announced March 2026.

    Comments: First three authors contributed equally

  9. arXiv:2509.15858  [pdf, ps, other

    cs.IR cs.LG

    Optimizing Product Deduplication in E-Commerce with Multimodal Embeddings

    Authors: Aysenur Kulunk, Berk Taskin, M. Furkan Eseoglu, H. Bahadir Sahin

    Abstract: In large scale e-commerce marketplaces, duplicate product listings frequently cause consumer confusion and operational inefficiencies, degrading trust on the platform and increasing costs. Traditional keyword-based search methodologies falter in accurately identifying duplicates due to their reliance on exact textual matches, neglecting semantic similarities inherent in product titles. To address… ▽ More

    Submitted 1 December, 2025; v1 submitted 19 September, 2025; originally announced September 2025.

    Comments: 8 pages, accepted to 2025 IEEE International Conference on Big Data, Industrial and Goverment Track

  10. Processing-in-memory for genomics workloads

    Authors: William Andrew Simon, Leonid Yavits, Konstantina Koliogeorgi, Yann Falevoz, Yoshihiro Shibuya, Dominique Lavenier, Irem Boybat, Klea Zambaku, Berkan Şahin, Mohammad Sadrosadati, Onur Mutlu, Abu Sebastian, Rayan Chikhi, The BioPIM Consortium, Can Alkan

    Abstract: Low-cost, high-throughput DNA and RNA sequencing (HTS) data is the backbone of the life sciences. Genome sequencing is now becoming a part of Predictive, Preventive, Personalized, and Participatory (termed 'P4') medicine. All genomic data are currently processed in energy-hungry computer clusters and centers, necessitating data transfer, consuming substantial energy, and wasting valuable time. The… ▽ More

    Submitted 4 February, 2026; v1 submitted 31 May, 2025; originally announced June 2025.

    Journal ref: IEEE Micro, 46 (2): 70-80, 2026

  11. arXiv:2505.03679  [pdf, other

    cs.CV

    CaRaFFusion: Improving 2D Semantic Segmentation with Camera-Radar Point Cloud Fusion and Zero-Shot Image Inpainting

    Authors: Huawei Sun, Bora Kunter Sahin, Georg Stettinger, Maximilian Bernhard, Matthias Schubert, Robert Wille

    Abstract: Segmenting objects in an environment is a crucial task for autonomous driving and robotics, as it enables a better understanding of the surroundings of each agent. Although camera sensors provide rich visual details, they are vulnerable to adverse weather conditions. In contrast, radar sensors remain robust under such conditions, but often produce sparse and noisy data. Therefore, a promising appr… ▽ More

    Submitted 6 May, 2025; originally announced May 2025.

    Comments: Accepted at RA-L 2025

  12. arXiv:2505.01912  [pdf, ps, other

    cs.LG cond-mat.mtrl-sci cs.AI

    BOOM: Benchmarking Out-Of-distribution Molecular Property Predictions of Machine Learning Models

    Authors: Evan R. Antoniuk, Shehtab Zaman, Tal Ben-Nun, Peggy Li, James Diffenderfer, Busra Sahin, Obadiah Smolenski, Tim Hsu, Anna M. Hiszpanski, Kenneth Chiu, Bhavya Kailkhura, Brian Van Essen

    Abstract: Data-driven molecular discovery leverages artificial intelligence/machine learning (AI/ML) and generative modeling to filter and design novel molecules. Discovering novel molecules requires accurate out-of-distribution (OOD) predictions, but ML models struggle to generalize OOD. Currently, no systematic benchmarks exist for molecular OOD prediction tasks. We present $\mathbf{BOOM}$, $\mathbf{b}$en… ▽ More

    Submitted 19 December, 2025; v1 submitted 3 May, 2025; originally announced May 2025.

  13. arXiv:2312.16870  [pdf, other

    cs.DC

    ANKA: A Decentralized Blockchain-based Energy Marketplace for Battery-powered Devices

    Authors: Burak Can Sahin, Abdulrezzak Zekiye, Oznur Ozkasap

    Abstract: For the purpose of enabling, democratizing, and reducing the fees of peer-to-peer energy trading for battery-powered devices, we propose ANKA as a fully decentralized energy marketplace for peers with battery-powered devices. ANKA utilizes state-of-the-art technologies, namely blockchain, smart contracts, and decentralized applications. Within this marketplace, users who possess surplus energy act… ▽ More

    Submitted 28 December, 2023; originally announced December 2023.

    Comments: A shorter version of this paper was presented as a poster paper in the Fifth ACM International Workshop on Blockchain-enabled Networked Sensor Systems (BlockSys)

  14. Communication-Efficient Zeroth-Order Distributed Online Optimization: Algorithm, Theory, and Applications

    Authors: Ege C. Kaya, M. Berk Sahin, Abolfazl Hashemi

    Abstract: This paper focuses on a multi-agent zeroth-order online optimization problem in a federated learning setting for target tracking. The agents only sense their current distances to their targets and aim to maintain a minimum safe distance from each other to prevent collisions. The coordination among the agents and dissemination of collision-prevention information is managed by a central server using… ▽ More

    Submitted 8 June, 2023; originally announced June 2023.

    Comments: 21 pages, 5 figures, and this paper has been accepted by IEEE Access

  15. arXiv:2212.03616  [pdf, other

    eess.IV cs.MM

    Image Compression With Learned Lifting-Based DWT and Learned Tree-Based Entropy Models

    Authors: Ugur Berk Sahin, Fatih Kamisli

    Abstract: This paper explores learned image compression based on traditional and learned discrete wavelet transform (DWT) architectures and learned entropy models for coding DWT subband coefficients. A learned DWT is obtained through the lifting scheme with learned nonlinear predict and update filters. Several learned entropy models are proposed to exploit inter and intra-DWT subband coefficient dependencie… ▽ More

    Submitted 7 December, 2022; originally announced December 2022.

    Comments: 11 pages, 17 figures

  16. arXiv:1702.03654  [pdf, other

    cs.CL

    A Morphology-aware Network for Morphological Disambiguation

    Authors: Eray Yildiz, Caglar Tirkaz, H. Bahadir Sahin, Mustafa Tolga Eren, Ozan Sonmez

    Abstract: Agglutinative languages such as Turkish, Finnish and Hungarian require morphological disambiguation before further processing due to the complex morphology of words. A morphological disambiguator is used to select the correct morphological analysis of a word. Morphological disambiguation is important because it generally is one of the first steps of natural language processing and its performance… ▽ More

    Submitted 13 February, 2017; originally announced February 2017.

    Comments: 6 pages, 1 figure, Thirtieth AAAI Conference on Artificial Intelligence. 2016

  17. arXiv:1702.02363  [pdf, other

    cs.CL

    Automatically Annotated Turkish Corpus for Named Entity Recognition and Text Categorization using Large-Scale Gazetteers

    Authors: H. Bahadir Sahin, Caglar Tirkaz, Eray Yildiz, Mustafa Tolga Eren, Ozan Sonmez

    Abstract: Turkish Wikipedia Named-Entity Recognition and Text Categorization (TWNERTC) dataset is a collection of automatically categorized and annotated sentences obtained from Wikipedia. We constructed large-scale gazetteers by using a graph crawler algorithm to extract relevant entity and domain information from a semantic knowledge base, Freebase. The constructed gazetteers contains approximately 300K e… ▽ More

    Submitted 9 February, 2017; v1 submitted 8 February, 2017; originally announced February 2017.

    Comments: 10 page, 1 figure, white paper, update: added correct download link for dataset