BriefGPT.xyz
Apr, 2023
非凸非凹极小极大优化的高阶方法
Beyond first-order methods for non-convex non-concave min-max optimization
HTML
PDF
Abhijeet Vyas, Brian Bullins
TL;DR
使用高阶方法结合离散/连续时间分析，研究了结构化的非凸非凹min-max问题中算子范数最小化问题的近似最优解，与一阶方法相比，实验结果表明其具有显著优势。
Abstract
We propose a study of
structured
non-convex
non-concave
min-max
problems which goes beyond standard first-order approaches. Inspired by th
→