paper-with-me

홈 › Papers

Can Single-Shuffle SGD be Better than Reshuffling SGD and GD?

2021-03-12 · Chulhee Yun, Suvrit Sra, Ali Jadbabaie

We propose matrix norm inequalities that extend the Recht-R\'e (2012) conjecture on a noncommutative AM-GM inequality by supplementing it with another inequality that accounts for single-shuffle, which is a widely used without-replacement sampling scheme that shuffles only once in the beginning and is overlooked in the Recht-R\'e conjecture. Instead of general positive semidefinite matrices, we restrict our attention to positive definite matrices with small enough condition numbers, which are more relevant to matrices that arise in the analysis of SGD. For such matrices, we conjecture that the means of matrix products corresponding to with- and without-replacement variants of SGD satisfy a series of spectral norm inequalities that can be summarized as: "single-shuffle SGD converges faster than random-reshuffle SGD, which is in turn faster than with-replacement SGD." We present theorems that support our conjecture by proving several special cases.

📄 PDF Abstract BibTeX arXiv:2103.07079

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

FedShuffle: Recipes for Better Use of Local Work in Federated Learning

2022-04-27 · Samuel Horváth, Maziar Sanjabi, Lin Xiao, Peter Richtárik 외

The practice of applying several local updates before aggregation across clients has been empirically shown to be a successful approach to overcoming the communication bottleneck in Federated Learning (FL). Such methods …

Federated Learning

Learning to Shuffle: Block Reshuffling and Reversal Schemes for Stochastic Optimization

2026-03-31 · Lam M. Nguyen, Dzung T. Phan, Jayant Kalagnanam arxiv

Shuffling strategies for stochastic gradient descent (SGD), including incremental gradient, shuffle-once, and random reshuffling, are supported by rigorous convergence analyses for arbitrary within-epoch permutations. In…

Stochastic Optimization

Random Reshuffling: Simple Analysis with Vast Improvements

2020-06-10 · NeurIPS 2020 12 · Konstantin Mishchenko, Ahmed Khaled, Peter Richtárik

Random Reshuffling (RR) is an algorithm for minimizing finite-sum functions that utilizes iterative gradient descent steps in conjunction with data reshuffling. Often contrasted with its sibling Stochastic Gradient Desce…

Stochastic Extragradient with Random Reshuffling: Improved Convergence for Variational Inequalities

2024-03-11 · Konstantinos Emmanouilidis, René Vidal, Nicolas Loizou

The Stochastic Extragradient (SEG) method is one of the most popular algorithms for solving finite-sum min-max optimization and variational inequality problems (VIPs) appearing in various machine learning tasks. However,…

Experience Replay with Random Reshuffling

2025-03-04 · Yasuhiro Fujita

Experience replay is a key component in reinforcement learning for stabilizing learning and improving sample efficiency. Its typical implementation samples transitions with replacement from a replay buffer. In contrast, …

Deep Reinforcement Learningreinforcement-learningReinforcement Learning