3 papers
cs.LG2026
Understanding Schedule-Free Methods in Nonconvex Optimization: Rate Guarantees and Escaping Saddles
Jiseok Chae, Donghwan Kim
Schedule-Free methods have attracted growing interest for alleviating the burden of designing and tuning a learning rate scheduler, while matching and sometimes even outperforming…
cs.LG2024
Stochastic Extragradient with Flip-Flop Shuffling & Anchoring: Provable Improvements
Jiseok Chae, Chulhee Yun, Donghwan Kim
In minimax optimization, the extragradient (EG) method has been extensively studied because it outperforms the gradient descent-ascent method in convex-concave (C-C) problems. Yet,…
math.OC2023
Two-timescale Extragradient for Finding Local Minimax Points
Jiseok Chae, Kyuwon Kim, Donghwan Kim
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 t…