Efficient Algorithms for Smooth Minimax Optimization
Kiran K. Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh
–Neural Information Processing Systems
In terms of g(, y), we consider two settings - strongly convex and nonconvex - and improve upon the best known rates in both. For strongly-convex g(, y), y, we propose a new direct optimal algorithm combining Mirror-Prox and Nesterov's AGD, and show that it can find global optimum in Õ (1/k
Neural Information Processing Systems
Feb-11-2026, 08:55:52 GMT
- Country:
- Asia
- India (0.04)
- Middle East > Jordan (0.04)
- North America
- Canada > British Columbia
- United States
- Illinois (0.04)
- Washington > King County
- Seattle (0.04)
- Asia
- Technology: