Mher Safaryan
King Abdullah University of Science and Technology
H-index: 9
Asia-Saudi Arabia
Top articles of Mher Safaryan
Title | Journal | Author(s) | Publication Date |
---|---|---|---|
AsGrad: A Sharp Unified Analysis of Asynchronous-SGD Algorithms | Rustem Islamov Mher Safaryan Dan Alistarh | 2023/10/31 | |
Knowledge Distillation Performs Partial Variance Reduction | Mher Safaryan Alexandra Peste Dan Alistarh | 2023/5/27 | |
Distributed Newton-type methods with communication compression and bernoulli aggregation | Transactions on Machine Learning Research (TMLR), 2023 | Rustem Islamov Xun Qian Slavomír Hanzely Mher Safaryan Peter Richtárik | 2022/6/7 |
On estimates for maximal operators associated with tangential regions | Mher Safaryan | 2022/2/17 | |
Gradskip: Communication-accelerated local gradient methods with better computational complexity | arXiv preprint arXiv:2210.16402 | Artavazd Maranjyan Mher Safaryan Peter Richtárik | 2022/10/28 |
FedNL: Making Newton-type methods applicable to federated learning | International Conference on Machine Learning (ICML), 2022 | Mher Safaryan Rustem Islamov Xun Qian Peter Richtárik | 2021/6/5 |
On Generalizations of Fatou’s Theorem in for Convolution Integrals with General Kernels | The Journal of Geometric Analysis | MH Safaryan | 2021/4 |
Smoothness matrices beat smoothness constants: Better communication compression techniques for distributed optimization | Advances in Neural Information Processing Systems (NeurIPS) | Mher Safaryan Filip Hanzely Peter Richtárik | 2021/12/6 |
Basis Matters: Better Communication-Efficient Second Order Methods for Federated Learning | Xun Qian Rustem Islamov Mher Safaryan Peter Richtárik | 2021/11/2 | |
Theoretically Better and Numerically Faster Distributed Optimization with Smoothness-Aware Quantization Techniques | Bokun Wang Mher Safaryan Peter Richtárik | 2021/6/7 | |
A surprisingly effective algorithm for the simplification of integrals and sums arising in the partial differential equations and numerical methods | Diogo A Gomes Mher Safaryan Ricardo de Lima Ribeiro Mohammed Sayyari | 2020 | |
Optimal gradient compression for distributed and federated learning | arXiv preprint arXiv:2010.03246 | Alyazeed Albasyoni Mher Safaryan Laurent Condat Peter Richtárik | 2020/10/7 |
On Biased Compression for Distributed Learning | Journal of Machine Learning Research (JMLR), 2023 | Aleksandr Beznosikov Samuel Horváth Peter Richtárik Mher Safaryan | 2020/2/27 |
Uncertainty principle for communication compression in distributed and federated learning and the search for an optimal compressor | Information and Inference: A Journal of the IMA, 2021 | Mher Safaryan Egor Shulgin Peter Richtárik | 2020/2/20 |