activity
20222026
collaborators

6 papers

math.OC2026

Random Reshuffling Dominates Stochastic Gradient Descent

Zijian Liu

Stochastic Gradient Descent () is one of the most classical optimization algorithms with favorable theoretical guarantees, yet the practical implementation of $\texts…

math.OC2025

Improved Last-Iterate Convergence of Shuffling Gradient Methods for Nonsmooth Convex Optimization

Zijian Liu, Zhengyuan Zhou

We study the convergence of the shuffling gradient method, a popular algorithm employed to minimize the finite-sum function with regularization, in which functions are passed to ap…

math.OC2024

Nonconvex Stochastic Optimization under Heavy-Tailed Noises: Optimal Convergence without Gradient Clipping

Zijian Liu, Zhengyuan Zhou

Recently, the study of heavy-tailed noises in first-order nonconvex stochastic optimization has gotten a lot of attention since it was recognized as a more realistic condition as s…

cs.LG2024

On the Last-Iterate Convergence of Shuffling Gradient Methods

Zijian Liu, Zhengyuan Zhou

Shuffling gradient methods are widely used in modern machine learning tasks and include three popular implementations: Random Reshuffle (RR), Shuffle Once (SO), and Incremental Gra…

cs.LG2023

Revisiting the Last-Iterate Convergence of Stochastic Gradient Methods

Zijian Liu, Zhengyuan Zhou

In the past several years, the last-iterate convergence of the Stochastic Gradient Descent (SGD) algorithm has triggered people's interest due to its good performance in practice b…

cs.LG2022

META-STORM: Generalized Fully-Adaptive Variance Reduced SGD for Unbounded Functions

Zijian Liu, Ta Duy Nguyen, Thien Hang Nguyen +2

We study the application of variance reduction (VR) techniques to general non-convex stochastic optimization problems. In this setting, the recent work STORM [Cutkosky-Orabona '19]…