Meisam Razaviyayn

Solving a Class of Non-Convex Min-Max Games Using Iterative First Order Methods

2019 · arXiv (Cornell University)

Recent applications that arise in machine learning have surged significant interest in solving min-max saddle point games. This problem has been extensively studied in the convex-concave regime for which a global equilibrium solution can be …

ATLAS: Learning to Optimally Memorize the Context at Test Time

2025 · arXiv (Cornell University)

Transformers have been established as the most popular backbones in sequence modeling, mainly due to their effectiveness in in-context retrieval tasks and the ability to learn at scale. Their quadratic memory and time complexity, however, …