1 citations · 1 across the 7 of their papers we have counts for
5 papers · 1 filter
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…
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.…