Kfir Yehuda Levy

Optimizer Selection Based On Function-Proxy Proximity

Probing in the Dark: State Entropy Maximization for POMDPs

Gradient-Variation Online Adaptivity for Accelerated Optimization with Hölder Smoothness

On the Convergence of Single-Timescale Actor-Critic

Prediction-Powered Semi-Supervised Learning with Online Power Tuning

Global Convergence of Policy Gradient in Average Reward MDPs

Non-rectangular Robust MDPs with Normed Uncertainty Sets

Do Stochastic, Feel Noiseless: Stable Stochastic Optimization via a Double Momentum Mechanism

Beyond Communication Overhead: A Multilevel Monte Carlo Approach for Mitigating Compression Bias in Distributed Learning

Enhancing Parallelism in Decentralized Stochastic Convex Optimization

Convergence of Clipped SGD on Convex $(L_0,L_1)$-Smooth Functions

Privacy-Preserving Federated Convex Optimization: Balancing Partial-Participation and Efficiency via Noise Cancellation

Improved Sample Complexity for Global Convergence of Actor-Critic Algorithms