Last Iterate is Slower than Averaged Iterate in Smooth Convex-Concave
Saddle Point Problems

v1v2 (latest)

Last Iterate is Slower than Averaged Iterate in Smooth Convex-Concave Saddle Point Problems

31 January 2020

Asuman Ozdaglar

ArXiv (abs)PDF HTML

Papers citing "Last Iterate is Slower than Averaged Iterate in Smooth Convex-Concave Saddle Point Problems"

6 / 56 papers shown

Title
Efficient Methods for Structured Nonconvex-Nonconcave Min-Max Optimization Jelena Diakonikolas C. Daskalakis Michael I. Jordan 184 149 0 31 Oct 2020
LEAD: Min-Max Optimization from a Physical Perspective Reyhane Askari Hemmat Amartya Mitra Guillaume Lajoie Ioannis Mitliagkas 151 1 0 26 Oct 2020
Tight last-iterate convergence rates for no-regret learning in multi-player games Noah Golowich S. Pattathil C. Daskalakis 160 84 0 26 Oct 2020
A Unified Analysis of First-Order Methods for Smooth Games via Integral Quadratic Constraints Guodong Zhang Xuchao Bao Laurent Lessard Roger C. Grosse 107 25 0 23 Sep 2020
The Complexity of Constrained Min-Max Optimization C. Daskalakis Stratis Skoulakis Manolis Zampetakis 171 138 0 21 Sep 2020
Linear Last-iterate Convergence in Constrained Saddle-point Optimization Chen-Yu Wei Chung-Wei Lee Mengxiao Zhang Haipeng Luo 168 11 0 16 Jun 2020