Safaryan, Mher

14 publications

TMLR 2025 GradSkip: Communication-Accelerated Local Gradient Methods with Better Computational Complexity Arto Maranjyan, Mher Safaryan, Peter Richtárik

ICLR 2025 LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics Thomas Robert, Mher Safaryan, Ionut-Vlad Modoranu, Dan Alistarh

NeurIPS 2025 Unified Scaling Laws for Compressed Representations Andrei Panferov, Alexandra Volkova, Ionut-Vlad Modoranu, Vage Egiazarian, Mher Safaryan, Dan Alistarh

AISTATS 2024 AsGrad: A Sharp Unified Analysis of Asynchronous-SGD Algorithms Rustem Islamov, Mher Safaryan, Dan Alistarh

NeurIPS 2024 MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence Ionut-Vlad Modoranu, Mher Safaryan, Grigory Malinovsky, Eldar Kurtic, Thomas Robert, Peter Richtárik, Dan Alistarh

NeurIPS 2024 The Iterative Optimal Brain Surgeon: Faster Sparse Recovery by Leveraging Second-Order Information Diyuan Wu, Ionut-Vlad Modoranu, Mher Safaryan, Denis Kuznedelev, Dan Alistarh

TMLR 2023 Distributed Newton-Type Methods with Communication Compression and Bernoulli Aggregation Rustem Islamov, Xun Qian, Slavomir Hanzely, Mher Safaryan, Peter Richtárik

NeurIPS 2023 Knowledge Distillation Performs Partial Variance Reduction Mher Safaryan, Alexandra Peste, Dan Alistarh

JMLR 2023 On Biased Compression for Distributed Learning Aleksandr Beznosikov, Samuel Horváth, Peter Richtárik, Mher Safaryan

AISTATS 2022 Basis Matters: Better Communication-Efficient Second Order Methods for Federated Learning Xun Qian, Rustem Islamov, Mher Safaryan, Peter Richtarik

ICML 2022 FedNL: Making Newton-Type Methods Applicable to Federated Learning Mher Safaryan, Rustem Islamov, Xun Qian, Peter Richtarik

NeurIPS 2022 Theoretically Better and Numerically Faster Distributed Optimization with Smoothness-Aware Quantization Techniques Bokun Wang, Mher Safaryan, Peter Richtarik

NeurIPS 2021 Smoothness Matrices Beat Smoothness Constants: Better Communication Compression Techniques for Distributed Optimization Mher Safaryan, Filip Hanzely, Peter Richtarik

ICML 2021 Stochastic Sign Descent Methods: New Algorithms and Better Theory Mher Safaryan, Peter Richtarik