Random Reshuffling

Latest papers

11 papers2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Large-Step Last-Iterate Convergence of Random-Reshuffling Stochastic Gradient Descent
Oct 14, 2026Zijun Chen, Zihan ZhangStochastic Optimization Last-Iterate Convergence
Department of Computer Science and Engineering, Hong Kong University of Science and Technology
Closed-Form Noise Calibration Against Membership Inference for Random-Allocation DP-SGD
Oct 7, 2026Murat Bilgehan Ertan, Marten van DijkRandom Reshuffling Differentially Private Stochastic Gradient Descent
Affiliated with Vrije Universiteit Amsterdam.
Stochastic Optimization Under Power-Law Spectra: Tight Bounds and Shuffling Analysis
Sep 28, 2026Thomas Dybdahl Ahle, Yaroslav Bulatov, Christopher De Sa +1Random Reshuffling Stochastic Optimization Convergence
Normal Computing · Cornell University · Stanford University
Centered Permutation Prefixes for SGD with Random Reshuffling: Sharp Rates, Hölder Geometry, and Composite Proximal Extensions
Sep 4, 2026Jiaxiang LiRandom Reshuffling Stochastic Optimization Convergence
Grado Department of Industrial and Systems Engineering, Virginia Tech.
Theoretical Foundations of Communication-Efficient, Robust, and Practical Distributed and Federated Optimization
Aug 6, 2026Grigory MalinovskyByzantine-Robust Federated Learning Communication-Efficient Distributed Training
King Abdullah University of Science and Technology Thuwal, Kingdom of Saudi Arabia
Stochastic Saddle Avoidance Beyond Unit Excitation and Smoothness: A Pathwise Lyapunov-Perron Framework
Aug 4, 2026Junwen Qiu, Bohao Ma, Andre Milzarek +1Stochastic Optimization Nonconvex Stochastic Optimization
Industrial Systems Engineering and Management, National University of Singapore, Singapore. · School of Data Science, The Chinese University of Hong Kong, Shenzhen, China.
Random Reshuffling Dominates Stochastic Gradient Descent
Jun 30, 2026Zijian LiuStochastic Optimization Convergence Random Reshuffling
Stern School of Business, New York University
Rethinking Dense Sequential Chains: Reasoning Language Models Can Extract Answers from Sparse, Order-Shuffling Chain-of-Thoughts
May 8, 2026Yi-Chang Chen, Feng-Ting Liao, Da-shan Shiu +1CoT Reasoning Causal Interventions in Language Models
MediaTek Research · Artificial Intelligence Center of Research Excellence, National Taiwan University
Shuffling the Data, Stretching the Step-size: Sharper Bias in constant step-size SGD
Apr 11, 2026Konstantinos Emmanouilidis, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Rene VidalRandom Reshuffling Richardson Extrapolation
Department of Computer Science, University of Pennsylvania · University of Wisconsin-Madison, Archimedes Research Unit
Learning to Shuffle: Block Reshuffling and Reversal Schemes for Stochastic Optimization
Mar 31, 2026Lam M. Nguyen, Dzung T. Phan, Jayant KalagnanamStochastic Optimization Convergence Stochastic Gradient Descent
IBM Research, Thomas J. Watson Research Center, Yorktown Heights, NY, USA
Shuffling the Stochastic Mirror Descent via Dual Lipschitz Continuity and Kernel Conditioning
Mar 17, 2026Junwen Qiu, Leilei Mei, Junyu ZhangRandom Reshuffling Stochastic Optimization
Industrial Systems Engineering and Management, National University of Singapore

Oct 14, 2026J/K move · Enter open · S save

Large-Step Last-Iterate Convergence of Random-Reshuffling Stochastic Gradient Descent

Zijun Chen, Zihan Zhang

Department of Computer Science and Engineering, Hong Kong University of Science and Technology

Stochastic Optimization Last-Iterate Convergence Stochastic Optimization Convergence Stochastic Gradient Descent Random Reshuffling

Open paper AskPDF arXiv

Random reshuffling stochastic gradient descent (RR-SGD) is widely used for finite-sum optimization in machine learning. For convex

L

-smooth components, recent work establishes convergence guarantees for an averaged iterate with component stepsizes as large as order

1/L

. However, the final iterate is a natural output in practice, and existing last-iterate guarantees in this setting require stepsizes that scale inversely with the number of components

n

. We establish an expected objective-gap bound for the last iterate of standard RR-SGD on unconstrained problems with a constant component stepsize satisfying

0<η\lesssim 1/(L(1 + \log(nK)))

, where

K

is the number of epochs. By retaining the sampling bias at random comparison points, we remove the explicit

1/n

factor from the stepsize restriction. Combined with existing small-step bounds, our result matches the corresponding averaged-iterate convergence rate up to logarithmic factors.