April 23, 2024, 4:44 a.m. | Jiseok Chae, Kyuwon Kim, Donghwan Kim

cs.LG updates on arXiv.org arxiv.org

arXiv:2305.16242v2 Announce Type: replace-cross
Abstract: Minimax problems are notoriously challenging to optimize. However, we present that the two-timescale extragradient method can be a viable solution. By utilizing dynamical systems theory, we show that it converges to points that satisfy the second-order necessary condition of local minimax points, under mild conditions that the two-timescale gradient descent ascent fails to work. This work provably improves upon all previous results on finding local minimax points, by eliminating a crucial assumption that the Hessian …

abstract arxiv cs.lg however math.oc minimax show solution systems theory timescale type

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote

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