Mher Safaryan

Cited by

	All	Since 2020
Citations	632	612
h-index	11	11
i10-index	13	12

220

110

165

201520162017201820192020202120222023202420252 3 3 7 2 19 90 119 150 218 13

Public access

View all

2 articles

0 articles

available

not available

Based on funding mandates

Co-authors

Peter RichtarikProfessor, KAUSTVerified email at kaust.edu.sa
Rustem IslamovPhD student, University of BaselVerified email at unibas.ch
Xun QianResearcher, Shanghai AI LabVerified email at pjlab.org.cn
Samuel HorvathMohamed bin Zayed University of Artificial Intelligence (MBZUAI)Verified email at mbzuai.ac.ae
Aleksandr BeznosikovPhD, Moscow Institute of Physics and TechnologyVerified email at phystech.edu
Dan AlistarhProfessor at IST AustriaVerified email at ist.ac.at
Sergey Davidovassociate professor, Yerevan State UniversityVerified email at ysu.am
Grigori KaragulyanInstitute of Mathematics, Armenian National Academy of SciencesVerified email at ysu.am
Filip HanzelyVerified email at kaust.edu.sa
Laurent CondatSenior Research Scientist, King Abdullah University of Science and Technology (KAUST), Saudi ArabiaVerified email at kaust.edu.sa
Egor ShulginPhD candidate, KAUSTVerified email at kaust.edu.sa
Bokun WangTexas A&M UniversityVerified email at tamu.edu
Ionut-Vlad ModoranuPhD student at Institute of Science and Technology Austria (ISTA)Verified email at ist.ac.at
Slavomír HanzelyPostdoctoral Researcher, MBZUAIVerified email at mbzuai.ac.ae
Arto MaranjyanPhD student, King Abdullah University of Science and Technology (KAUST)Verified email at kaust.edu.sa
Thomas ROBERTMaster student at École polytechnique - MVAVerified email at polytechnique.edu
Davit KaragulyanPhD in mathemtics, KTH Royal Institute of TechnologyVerified email at kth.se
Alexandra PesteInstitute of Science and Technology AustriaVerified email at ist.ac.at
Eldar KurticNeural Magic and IST AustriaVerified email at ist.ac.at
Grigory MalinovskyPhD student, King Abdullah University of Science and TechnologyVerified email at kaust.edu.sa

Mher Safaryan

Postdoctoral MSCA Fellow, IST Austria

Verified email at ist.ac.at - Homepage

Optimization Machine Learning Harmonic Analysis


Title Sort by citations Sort by year Sort by title	Cited by Cited by	Year
On Biased Compression for Distributed Learning A Beznosikov, S Horváth, P Richtárik, M Safaryan Journal of Machine Learning Research (JMLR), 2023, 2020	195	2020
FedNL: Making Newton-type methods applicable to federated learning M Safaryan, R Islamov, X Qian, P Richtárik International Conference on Machine Learning (ICML), 2022, 2021	91	2021
Optimal Gradient Compression for Distributed and Federated Learning A Albasyoni, M Safaryan, L Condat, P Richtárik arXiv preprint arXiv:2010.03246, 2020	64	2020
Uncertainty principle for communication compression in distributed and federated learning and the search for an optimal compressor M Safaryan, E Shulgin, P Richtárik Information and Inference: A Journal of the IMA, 2021, 2020	64	2020
Stochastic Sign Descent Methods: New Algorithms and Better Theory M Safaryan, P Richtárik International Conference on Machine Learning (ICML), 2021, 2019	55*	2019
Smoothness matrices beat smoothness constants: Better communication compression techniques for distributed optimization M Safaryan, F Hanzely, P Richtárik Advances in Neural Information Processing Systems (NeurIPS) 34, 25688-25702, 2021	32	2021
Basis Matters: Better Communication-Efficient Second Order Methods for Federated Learning X Qian, R Islamov, M Safaryan, P Richtárik International Conference on Artificial Intelligence and Statistics (AISTATS …, 2021	24	2021
Construction of free g-dimonoids Y Movsisyan, S Davidov, M Safaryan Algebra and discrete mathematics, 2014	18	2014
Theoretically Better and Numerically Faster Distributed Optimization with Smoothness-Aware Quantization Techniques B Wang, M Safaryan, P Richtárik Advances in Neural Information Processing Systems (NeurIPS) 2022, 2021	15*	2021
AsGrad: A Sharp Unified Analysis of Asynchronous-SGD Algorithms R Islamov, M Safaryan, D Alistarh International Conference on Artificial Intelligence and Statistics (AISTATS …, 2023	11	2023
Gradskip: Communication-accelerated local gradient methods with better computational complexity A Maranjyan, M Safaryan, P Richtárik arXiv preprint arXiv:2210.16402, 2022	11	2022
Distributed Newton-type methods with communication compression and bernoulli aggregation R Islamov, X Qian, S Hanzely, M Safaryan, P Richtárik Transactions on Machine Learning Research (TMLR), 2023, 2022	11	2022
On generalizations of Fatou’s theorem for the integrals with general kernels GA Karagulyan, MH Safaryan The Journal of Geometric Analysis 25, 1459-1475, 2015	10	2015
On Generalizations of Fatou’s Theorem in for Convolution Integrals with General Kernels MH Safaryan The Journal of Geometric Analysis 31 (4), 3280-3299, 2021	8	2021
On a theorem of Littlewood GA Karagulyan, MH Safaryan Hokkaido Mathematical Journal 46 (1), 87-106, 2017	6	2017
On an equivalence for differentiation bases of dyadic rectangles GA Karagulyan, DA Karagulyan, MH Safaryan Colloq. Math 146 (2), 295-307, 2017	6	2017
On an equivalency of rare differentiation bases of rectangles MH Safaryan Journal of Contemporary Mathematical Analysis (Armenian Academy of Sciences …, 2018	5	2018
Knowledge Distillation Performs Partial Variance Reduction M Safaryan, A Peste, D Alistarh Advances in Neural Information Processing Systems (NeurIPS) 2023, 2023	3	2023
LDAdam: Adaptive Optimization from Low-dimensional Gradient Statistics T Robert, M Safaryan, IV Modoranu, D Alistarh International Conference on Learning Representations (ICLR), 2025, 2024	2	2024
MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence IV Modoranu, M Safaryan, G Malinovsky, E Kurtic, T Robert, P Richtarik, ... Advances in Neural Information Processing Systems (NeurIPS) 2024, 2024	1	2024

The system can't perform the operation now. Try again later.

Articles 1–20

Citations per year

Duplicate citations

Merged citations

Add co-authorsCo-authors

Follow

Cited by

Co-authors