1 citations · 1 across the 7 of their papers we have counts for
9 papers
Linear Last-Iterate Convergence Rates for Optimistic Learning in Harmonic Games
John Lazarsfeld, Anas Barakat, Jacob Abernethy +4
We prove that the last iterate of Optimistic Follow-The-Regularized-Leader (OFTRL) converges at a linear rate to a Nash equilibrium in multiplayer harmonic games. Our result holds…
Learning in Continuous Games from Pairwise Preference Feedback
Anas Barakat
We study learning in continuous games when players receive only pairwise preference feedback, revealing which of two actions is preferred but neither payoff values nor preference m…
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…
Prompt Interference in LLM Post-Training: Why Pass@k Optimization Can Degrade Pass@1
Anas Barakat, Souradip Chakraborty, Khushbu Pahwa +1
Pass@ is a widely used performance metric for verifiable large language model tasks, including mathematical reasoning, code generation, and short-answer reasoning. It defines su…
Independent Policy Mirror Descent for Markov Potential Games: Scaling to Large Number of Players
Pragnya Alatur, Anas Barakat, Niao He
Markov Potential Games (MPGs) form an important sub-class of Markov games, which are a common framework to model multi-agent reinforcement learning problems. In particular, MPGs in…
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…
Independent Learning in Constrained Markov Potential Games
Philip Jordan, Anas Barakat, Niao He
Constrained Markov games offer a formal mathematical framework for modeling multi-agent reinforcement learning problems where the behavior of the agents is subject to constraints.…
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…