About

Research

Publications

Contact

I had the opportunity to contribute to the optimization and machine learning community through the following publications. They are organized by research area:

Publications: 3 NeurIPS, 3 ICML, 2 AISTATS, 1 SICON, 1 JMLR, 2 under review

Large-Scale Optimization

2021
• Peter Richtárik, Igor Sokolov, Ilyas Fatkhullin. EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback, NeurIPS 2021 oral. ▼ Poster
2022
• Peter Richtárik, Igor Sokolov, Ilyas Fatkhullin, Elnur Gasanov, Eduard Gorbunov, Zhize Li. 3PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy Aggregation, ICML 2022 spotlight. ▼ Poster
2023
• Ilyas Fatkhullin, Alexander Tyurin, Peter Richtárik. Momentum Provably Improves Error Feedback!, NeurIPS 2023. ▼ Poster
• Junchi Yang, Xiang Li, Ilyas Fatkhullin, Niao He. Two Sides of One Coin: the Limits of Untuned SGD and the Power of Adaptive Methods, NeurIPS 2023.

Reinforcement Learning and Control

2021
• Ilyas Fatkhullin, Boris Polyak. Optimizing Static Linear Feedback: Gradient Method, SIAM Journal on Control and Optimization, 2021.
2023
• Ilyas Fatkhullin, Anas Barakat, Anastasia Kireeva, Niao He. Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate Policies, ICML 2023. ▼ Poster
• Anas Barakat, Ilyas Fatkhullin, Niao He. Reinforcement Learning with General Utilities: Simpler Variance Reduction and Large State-Action Space, ICML 2023. ▼ Poster
• Jiduan Wu, Anas Barakat, Ilyas Fatkhullin, Niao He. Learning Zero-Sum Linear Quadratic Games with Improved Sample Complexity and Last-Iterate Convergence, preliminary version at CDC 2023, journal version under review

Theoretical Foundations

2022
• Ilyas Fatkhullin*, Jalal Etesami*, Niao He, Negar Kiyavash. Sharp Analysis of Stochastic Optimization under Global Kurdyka-Łojasiewicz Inequality, NeurIPS 2022. ▼ Poster
2023
• Ilyas Fatkhullin, Niao He, Yifan Hu. Stochastic Optimization under Hidden Convexity, preliminary version at OptML@NeurIPS 2023, journal version under review ▼ Poster
2024-2025
• Ilyas Fatkhullin, Niao He. Taming Nonconvex Stochastic Mirror Descent with General Bregman Divergence, AISTATS 2024. ▼ Poster
• Florian Hübler*, Ilyas Fatkhullin*, Niao He. From Gradient Clipping to Normalization for Heavy Tailed SGD, AISTATS 2025.

View all publications on Google Scholar