5 papers
Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit Feedback
Anas Barakat, Andreas Kontogiannis, Vasilis Pollatos +2
We study adversarial online learning with hidden-convex losses, i.e., nonconvex losses that become convex after a nonlinear reparameterization. Ghai, Lu and Hazan (2022) proved tha…
When and Why is Optimistic Multiplicative Weights Slow? The Geometry of Energy Dissipation
John Lazarsfeld, Anas Barakat, Georgios Piliouras +2
This paper studies the convergence of the Optimistic Multiplicative Weights Update algorithm (OMWU) in two player zero-sum games. Recent works have identified instances on which th…
Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-training
Anas Barakat, Souradip Chakraborty, Khushbu Pahwa +1
Pass@k is a widely used performance metric for verifiable large language model tasks, including mathematical reasoning, code generation, and short-answer reasoning. It defines succ…
Learning Zero-Sum Linear Quadratic Games with Improved Sample Complexity and Last-Iterate Convergence
Jiduan Wu, Anas Barakat, Ilyas Fatkhullin +1
Zero-sum Linear Quadratic (LQ) games are fundamental in optimal control and can be used (i)~as a dynamic game formulation for risk-sensitive or robust control and (ii)~as a benchma…
Policy Mirror Descent with Lookahead
Kimon Protopapas, Anas Barakat
Policy Mirror Descent (PMD) stands as a versatile algorithmic framework encompassing several seminal policy gradient algorithms such as natural policy gradient, with connections wi…