all AI news
Fundamental Benefit of Alternating Updates in Minimax Optimization
Feb. 19, 2024, 5:42 a.m. | Jaewook Lee, Hanseul Cho, Chulhee Yun
cs.LG updates on arXiv.org arxiv.org
Abstract: The Gradient Descent-Ascent (GDA) algorithm, designed to solve minimax optimization problems, takes the descent and ascent steps either simultaneously (Sim-GDA) or alternately (Alt-GDA). While Alt-GDA is commonly observed to converge faster, the performance gap between the two is not yet well understood theoretically, especially in terms of global convergence rates. To address this theory-practice gap, we present fine-grained convergence analyses of both algorithms for strongly-convex-strongly-concave and Lipschitz-gradient objectives. Our new iteration complexity upper bound of …
abstract algorithm arxiv benefit converge cs.lg faster gap gda gradient math.oc minimax optimization performance sim solve terms type updates
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Business Intelligence Manager
@ Sanofi | Budapest
Principal Engineer, Data (Hybrid)
@ Homebase | Toronto, Ontario, Canada