| Paper ID | MLSP-32.1 |
| Paper Title |
SOLVING A CLASS OF NON-CONVEX MIN-MAX GAMES USING ADAPTIVE MOMENTUM METHODS |
| Authors |
Babak Barazandeh, Splunk, United States; Davoud Ataee Tarzanagh, George Michailidis, University of Florida, United States |
| Session | MLSP-32: Optimization Algorithms for Machine Learning |
| Location | Gather.Town |
| Session Time: | Thursday, 10 June, 15:30 - 16:15 |
| Presentation Time: | Thursday, 10 June, 15:30 - 16:15 |
| Presentation |
Poster
|
| Topic |
Machine Learning for Signal Processing: [MLR-LEAR] Learning theory and algorithms |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
Adaptive momentum methods have recently attracted a lot of attention for training of deep neural networks. They use an exponential moving average of past gradients of the objective function to update both search directions and learning rates. However, these methods are not suited for solving min-max optimization problems that arise in training generative adversarial networks. In this paper, we propose an adaptive momentum min-max algorithm that generalizes adaptive momentum methods to the non-convex min-max regime. Further, we establish non-asymptotic rates of convergence for it when used in a reasonably broad class of non-convex min-max optimization problems. Experimental results illustrate its superior performance vis-a-vis benchmark methods for solving such problems. |
