Anas Barakat

Latest

• Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit Feedback
• When and Why is Optimistic Multiplicative Weights Slow? The Geometry of Energy Dissipation
• Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-training
• Convex Markov Games and Beyond: New Proof of Existence, Characterization and Learning Algorithms for Nash Equilibria
• Policy Gradients for Cumulative Prospect Theory in Reinforcement Learning
• On the Global Optimality of Policy Gradient Methods in General Utility Reinforcement Learning
• Online Multi-Agent Control with Adversarial Disturbances
• Optimistic Online Learning in Symmetric Cone Games
• Learning Zero-Sum Linear Quadratic Games with Improved Sample Complexity and Last Iterate Convergence
• Policy Mirror Descent with Lookahead
• Independent Learning in Constrained Markov Potential Games
• Learning Zero-Sum Linear Quadratic Games with Improved Sample Complexity
• Reinforcement Learning with General Utilities: Simpler Variance Reduction and Large State-Action Space
• Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate Policies
• Analysis of a Target-Based Actor-Critic Algorithm with Linear Function Approximation
• Contributions to non-convex stochastic optimization and reinforcement learning
• Stochastic optimization with momentum: convergence, fluctuations, and traps avoidance
• Convergence and Dynamical Behavior of the ADAM Algorithm for Non-Convex Stochastic Optimization
• Convergence Rates of a Momentum Algorithm with Bounded Adaptive Step Size for Non-Convex Optimization