Mher Safaryan

According to our database, Mher Safaryan authored at least 25 papers between 2020 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

MatryoshkaLoRA: Learning Accurate Hierarchical Low-Rank Representations for LLM Fine-Tuning.

Ionut-Vlad Modoranu, Mher Safaryan, Dan Alistarh

CoRR, May, 2026

Towards Robust Scaling Laws for Optimizers.

Alexandra Volkova, Mher Safaryan, Christoph H. Lampert, Dan Alistarh

CoRR, February, 2026

LoRDO: Distributed Low-Rank Optimization with Infrequent Communication.

Andrej Jovanovic, Alex Iacob, Mher Safaryan, Ionut-Vlad Modoranu, Lorenzo Sani, William F. Shen, Xinchi Qiu, Dan Alistarh, Nicholas D. Lane

CoRR, February, 2026

DASH: Faster Shampoo via Batched Block Preconditioning and Efficient Inverse-Root Solvers.

Ionut-Vlad Modoranu, Philip Zmushko, Erik Schultheis, Mher Safaryan, Dan Alistarh

CoRR, February, 2026

2025

CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training.

Soroush Tabesh, Mher Safaryan, Dan Alistarh

CoRR, October, 2025

MT-DAO: Multi-Timescale Distributed Adaptive Optimizers with Local Updates.

Alex Iacob, Andrej Jovanovic, Mher Safaryan, Meghdad Kurmanji, Lorenzo Sani, Samuel Horváth, William F. Shen, Xinchi Qiu, Nicholas D. Lane

CoRR, October, 2025

DES-LOC: Desynced Low Communication Adaptive Optimizers for Training Foundation Models.

Alex Iacob, Lorenzo Sani, Mher Safaryan, Paris Giampouras, Samuel Horváth, Andrej Jovanovic, Meghdad Kurmanji, Preslav Aleksandrov, William F. Shen, Xinchi Qiu, Nicholas D. Lane

CoRR, May, 2025

SVD-Free Low-Rank Adaptive Gradient Optimization for Large Language Models.

Ionut-Vlad Modoranu, Mher Safaryan, Erik Schultheis, Dan Alistarh

CoRR, May, 2025

GradSkip: Communication-Accelerated Local Gradient Methods with Better Computational Complexity.

Arto Maranjyan, Mher Safaryan, Peter Richtárik

Trans. Mach. Learn. Res., 2025

Unified Scaling Laws for Compressed Representations.

Andrei Panferov, Alexandra Volkova, Ionut-Vlad Modoranu, Vage Egiazarian, Mher Safaryan, Dan Alistarh

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics.

Thomas Robert, Mher Safaryan, Ionut-Vlad Modoranu, Dan Alistarh

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

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

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 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

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

AsGrad: A Sharp Unified Analysis of Asynchronous-SGD Algorithms.

Rustem Islamov, Mher Safaryan, Dan Alistarh

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

2023

Distributed Newton-Type Methods with Communication Compression and Bernoulli Aggregation.

Rustem Islamov, Xun Qian, Slavomír Hanzely, Mher Safaryan, Peter Richtárik

Trans. Mach. Learn. Res., 2023

On Biased Compression for Distributed Learning.

Aleksandr Beznosikov, Samuel Horváth, Peter Richtárik, Mher Safaryan

J. Mach. Learn. Res., 2023

Knowledge Distillation Performs Partial Variance Reduction.

Mher Safaryan, Alexandra Peste, Dan Alistarh

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

Theoretically Better and Numerically Faster Distributed Optimization with Smoothness-Aware Quantization Techniques.

Bokun Wang, Mher Safaryan, Peter Richtárik

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

FedNL: Making Newton-Type Methods Applicable to Federated Learning.

Mher Safaryan, Rustem Islamov, Xun Qian, Peter Richtárik

Proceedings of the International Conference on Machine Learning, 2022

Basis Matters: Better Communication-Efficient Second Order Methods for Federated Learning.

Xun Qian, Rustem Islamov, Mher Safaryan, Peter Richtárik

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

2021

Smoothness-Aware Quantization Techniques.

Bokun Wang, Mher Safaryan, Peter Richtárik

CoRR, 2021

Smoothness Matrices Beat Smoothness Constants: Better Communication Compression Techniques for Distributed Optimization.

Mher Safaryan, Filip Hanzely, Peter Richtárik

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Stochastic Sign Descent Methods: New Algorithms and Better Theory.

Mher Safaryan, Peter Richtárik

Proceedings of the 38th International Conference on Machine Learning, 2021

2020

Optimal Gradient Compression for Distributed and Federated Learning.

Alyazeed Albasyoni, Mher Safaryan, Laurent Condat, Peter Richtárik

CoRR, 2020

Uncertainty Principle for Communication Compression in Distributed and Federated Learning and the Search for an Optimal Compressor.

Mher Safaryan, Egor Shulgin, Peter Richtárik

CoRR, 2020