paper-with-me

Papers

SGDA with shuffling: faster convergence for nonconvex-PŁ minimax optimization

2022-10-12 · Hanseul Cho, Chulhee Yun

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., without-replacement sampling); however, there are few theoretical results on this approach for minimax algorithms, especially outside the easier-to-analyze (strongly-)monotone setups. To narrow this gap, we study the convergence bounds of SGDA with random reshuffling (SGDA-RR) for smooth nonconvex-nonconcave objectives with Polyak-{\L}ojasiewicz (P{\L}) geometry. We analyze both simultaneous and alternating SGDA-RR for nonconvex-P{\L} and primal-P{\L}-P{\L} objectives, and obtain convergence rates faster than with-replacement SGDA. Our rates extend to mini-batch SGDA-RR, recovering known rates for full-batch gradient descent-ascent (GDA). Lastly, we present a comprehensive lower bound for GDA with an arbitrary step-size ratio, which matches the full-batch upper bound for the primal-P{\L}-P{\L} case.

📄 PDF Abstract BibTeX arXiv:2210.05995

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Federated Minimax Optimization: Improved Convergence Analyses and Algorithms

2022-03-09 · Pranay Sharma, Rohan Panda, Gauri Joshi, Pramod K. Varshney

In this paper, we consider nonconvex minimax optimization, which is gaining prominence in many modern machine learning applications such as GANs. Large-scale edge-based collection of training data in these applications c…

Distributed OptimizationFederated Learning

Differentially Private SGDA for Minimax Problems

2022-01-22 · Zhenhuan Yang, Shu Hu, Yunwen Lei, Kush R. Varshney 외

Stochastic gradient descent ascent (SGDA) and its variants have been the workhorse for solving minimax problems. However, in contrast to the well-studied stochastic gradient descent (SGD) with differential privacy (DP) c…

Local Stochastic Gradient Descent Ascent: Convergence Analysis and Communication Efficiency

2021-02-25 · Yuyang Deng, Mehrdad Mahdavi

Local SGD is a promising approach to overcome the communication overhead in distributed learning by reducing the synchronization frequency among worker nodes. Despite the recent theoretical advances of local SGD in empir…

Solving a Class of Non-Convex Minimax Optimization in Federated Learning

2023-10-05 · NeurIPS 2023 11 · Xidong Wu, Jianhui Sun, Zhengmian Hu, Aidong Zhang 외

The minimax problems arise throughout machine learning applications, ranging from adversarial training and policy evaluation in reinforcement learning to AUROC maximization. To address the large-scale data challenges acr…

Federated Learning

Decentralized Riemannian Algorithm for Nonconvex Minimax Problems

2023-02-08 · Xidong Wu, Zhengmian Hu, Heng Huang

The minimax optimization over Riemannian manifolds (possibly nonconvex constraints) has been actively applied to solve many problems, such as robust dimensionality reduction and deep neural networks with orthogonal weigh…

Dimensionality Reduction