English
Related papers

Related papers: Can Single-Shuffle SGD be Better than Reshuffling …

200 papers

Adaptive gradient methods have attracted much attention of machine learning communities due to the high efficiency. However their acceleration effect in practice, especially in neural network training, is hard to analyze, theoretically. The…

Optimization and Control · Mathematics 2020-06-15 Xunpeng Huang , Hao Zhou , Runxin Xu , Zhe Wang , Lei Li

Recent theoretical results demonstrate that the convergence rates of permutation-based SGD (e.g., random reshuffling SGD) are faster than uniform-sampling SGD; however, these studies focus mainly on the large epoch regime, where the number…

Machine Learning · Computer Science 2025-06-05 Yujun Kim , Jaeyoung Cha , Chulhee Yun

We analyze a batched variant of Stochastic Gradient Descent (SGD) with weighted sampling distribution for smooth and non-smooth objective functions. We show that by distributing the batches computationally, a significant speedup in the…

Numerical Analysis · Mathematics 2017-03-02 Deanna Needell , Rachel Ward

When using stochastic gradient descent to solve large-scale machine learning problems, a common practice of data processing is to shuffle the training data, partition the data across multiple machines if needed, and then perform several…

Machine Learning · Statistics 2017-10-02 Qi Meng , Wei Chen , Yue Wang , Zhi-Ming Ma , Tie-Yan Liu

Symmetric Nonnegative Matrix Factorization (SNMF) models arise naturally as simple reformulations of many standard clustering algorithms including the popular spectral clustering method. Recent work has demonstrated that an elementary…

Computer Vision and Pattern Recognition · Computer Science 2016-09-20 Reza Borhani , Jeremy Watt , Aggelos Katsaggelos

Given a sequence $(M_{n},Q_{n})_{n\ge 1}$ of i.i.d.\ random variables with generic copy $(M,Q) \in GL(d, \R) \times \R^d$, we consider the random difference equation (RDE) $$ R_{n}=M_{n}R_{n-1}+Q_{n}, $$ $n\ge 1$, and assume the existence…

Probability · Mathematics 2013-04-04 Ewa Damek , Sebastian Mentemeier , Mariusz Mirek , Jacek Zienkiewicz

Stochastic gradient descent-ascent (SGDA) is one of the main workhorses for solving finite-sum minimax optimization problems. Most practical implementations of SGDA randomly reshuffle components and sequentially use them (i.e.,…

Optimization and Control · Mathematics 2023-02-21 Hanseul Cho , Chulhee Yun

Limiting Spectral Distributions (LSD) of real symmetric patterned matrices have been well-studied. In this article, we consider skew-symmetric/anti-symmetric patterned random matrices and establish the LSDs of several common matrices. For…

Probability · Mathematics 2014-02-18 Arup Bose , Soumendu Sundar Mukherjee

We aim to provide a unified convergence analysis for permutation-based Stochastic Gradient Descent (SGD), where data examples are permuted before each epoch. By examining the relations among permutations, we categorize existing…

Machine Learning · Computer Science 2025-01-28 Yipeng Li , Xinchen Lyu , Zhenyu Liu

The Stochastic Gradient Descent method (SGD) and its stochastic variants have become methods of choice for solving finite-sum optimization problems arising from machine learning and data science thanks to their ability to handle large-scale…

Optimization and Control · Mathematics 2024-03-06 Trang H. Tran , Quoc Tran-Dinh , Lam M. Nguyen

We study a distributed consensus-based stochastic gradient descent (SGD) algorithm and show that the rate of convergence involves the spectral properties of two matrices: the standard spectral gap of a weight matrix from the network…

Optimization and Control · Mathematics 2016-09-02 Avleen S. Bijral , Anand D. Sarwate , Nathan Srebro

We provide an improved analysis of normalized SGD showing that adding momentum provably removes the need for large batch sizes on non-convex objectives. Then, we consider the case of objectives with bounded second derivative and show that…

Machine Learning · Computer Science 2020-05-19 Ashok Cutkosky , Harsh Mehta

Random reshuffling, which randomly permutes the dataset each epoch, is widely adopted in model training because it yields faster convergence than with-replacement sampling. Recent studies indicate greedily chosen data orderings can further…

Machine Learning · Computer Science 2023-01-05 Yucheng Lu , Wentao Guo , Christopher De Sa

We study the deviation inequality for the spectral norm of structured random matrices with non-gaussian entries. In particular, we establish an optimal bound for the $p$-th moment of the spectral norm by transfering the spectral norm into…

Probability · Mathematics 2024-05-14 Guozheng Dai , Zhonggen Su

One approach for reducing run time and improving efficiency of machine learning is to reduce the convergence rate of the optimization algorithm used. Shuffling is an algorithm technique that is widely used in machine learning, but it only…

Machine Learning · Computer Science 2023-06-29 Yuetong Xu , Baharan Mirzasoleiman

The existing analysis of asynchronous stochastic gradient descent (SGD) degrades dramatically when any delay is large, giving the impression that performance depends primarily on the delay. On the contrary, we prove much better guarantees…

Optimization and Control · Mathematics 2023-04-21 Konstantin Mishchenko , Francis Bach , Mathieu Even , Blake Woodworth

We study generalization properties of random features (RF) regression in high dimensions optimized by stochastic gradient descent (SGD) in under-/over-parameterized regime. In this work, we derive precise non-asymptotic error bounds of RF…

Machine Learning · Statistics 2022-10-18 Fanghui Liu , Johan A. K. Suykens , Volkan Cevher

In this paper, we study the performance of a large family of SGD variants in the smooth nonconvex regime. To this end, we propose a generic and flexible assumption capable of accurate modeling of the second moment of the stochastic…

Optimization and Control · Mathematics 2020-06-15 Zhize Li , Peter Richtárik

Stochastic gradient descent (SGD) algorithm is the method of choice in many machine learning tasks thanks to its scalability and efficiency in dealing with large-scale problems. In this paper, we focus on the shuffling version of SGD which…

Machine Learning · Computer Science 2023-10-27 Lam M. Nguyen , Trang H. Tran

We study local SGD (also known as parallel SGD and federated averaging), a natural and frequently used stochastic distributed optimization method. Its theoretical foundations are currently lacking and we highlight how all existing error…