| EF21: A new, simpler, theoretically better, and practically faster error feedback P Richtárik, I Sokolov, I Fatkhullin Advances in Neural Information Processing Systems 34, 4384-4396, 2021 | 158 | 2021 |
| Optimizing static linear feedback: Gradient method I Fatkhullin, B Polyak SIAM Journal on Control and Optimization 59 (5), 3887-3911, 2021 | 107 | 2021 |
| EF21 with bells & whistles: Practical algorithmic extensions of modern error feedback I Fatkhullin, I Sokolov, E Gorbunov, Z Li, P Richtárik OptML Workshop at NeurIPS 2021, 2021 | 54 | 2021 |
| Stochastic policy gradient methods: Improved sample complexity for fisher-non-degenerate policies I Fatkhullin, A Barakat, A Kireeva, N He International Conference on Machine Learning 40, 9827-9869, 2023 | 44 | 2023 |
| 3PC: Three point compressors for communication-efficient distributed training and a better theory for lazy aggregation P Richtárik, I Sokolov, E Gasanov, I Fatkhullin, Z Li, E Gorbunov International Conference on Machine Learning, 18596-18648, 2022 | 32 | 2022 |
| Sharp analysis of stochastic optimization under global Kurdyka-Lojasiewicz inequality I Fatkhullin, J Etesami, N He, N Kiyavash Advances in Neural Information Processing Systems 35, 15836-15848, 2022 | 27 | 2022 |
| Two sides of one coin: the limits of untuned SGD and the power of adaptive methods J Yang, X Li, I Fatkhullin, N He Advances in Neural Information Processing Systems 36, 2024 | 18 | 2024 |
| Reinforcement Learning with General Utilities: Simpler Variance Reduction and Large State-Action Space A Barakat, I Fatkhullin, N He International Conference on Machine Learning 40, 1753-1800, 2023 | 17 | 2023 |
| Momentum Provably Improves Error Feedback! I Fatkhullin, A Tyurin, P Richtárik 37th Conference on Neural Information Processing Systems (NeurIPS 2023), 2023 | 16 | 2023 |
| Stochastic Optimization under Hidden Convexity I Fatkhullin, N He, Y Hu arXiv preprint arXiv:2401.00108, 2023 | 7 | 2023 |
| From Gradient Clipping to Normalization for Heavy Tailed SGD F Hübler, I Fatkhullin, N He arXiv preprint arXiv:2410.13849, 2024 | 4 | 2024 |
| Learning Zero-Sum Linear Quadratic Games with Improved Sample Complexity J Wu, A Barakat, I Fatkhullin, N He IEEE Conference on Decision and Control 62, 2023 | 1 | 2023 |
| Use of projective coordinate descent in the fekete problem BT Polyak, IF Fatkhullin Computational Mathematics and Mathematical Physics 60 (5), 795-807, 2020 | 1 | 2020 |
| Taming Nonconvex Stochastic Mirror Descent with General Bregman Divergence I Fatkhullin, N He AISTATS 2024, 2024 | | 2024 |
Niao HeAssociate Professor, ETH ZürichAdresse e-mail validée de inf.ethz.ch