Ilyas Fatkhullin

Reinforcement Learning with General Utilities: Simpler Variance Reduction and Large State-Action Space

Niao He, I. Fatkhullin, A. Barakat, 2023, ICML.

Optimizing Static Linear Feedback: Gradient Method

Boris Polyak, Ilyas Fatkhullin, Boris Polyak, 2020, SIAM J. Control. Optim..

Two Sides of One Coin: the Limits of Untuned SGD and the Power of Adaptive Methods

Niao He, Xiang Li, Junchi Yang, 2023, NeurIPS.

EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback pdf

Peter Richt'arik, Ilyas Fatkhullin, Igor Sokolov, 2021, NeurIPS.

Stochastic Optimization under Hidden Convexity

Niao He, Ilyas Fatkhullin, Yifan Hu, 2023, ArXiv.