3 accepted papers
Many modern machine learning problems require solving min-max saddle point games, whose computational complexity is NP-hard in general. To overcome this issue, most available algorithms aim for finding a first-order Nash equilibrium solution that always exists under mild assumptions. However, the pr…
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…
Min-max saddle point games appear in a wide range of applications in machine leaning and signal processing. Despite their wide applicability, theoretical studies are mostly limited to the special convex-concave structure. While some recent works generalized these results to special smooth non-convex…