Publications

Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation

Published in ArXiv, 2024

Grigory Malinovsky, Umberto Michieli, Hasan Abed Al Kader Hammoud, Taha Ceritli, Hayder Elesedy, Mete Ozay, Peter Richtárik

Byzantine Robustness and Partial Participation Can Be Achieved Simultaneously: Just Clip Gradient Differences

Published in The Thirty-Eighth Annual Conference on Neural Information Processing Systems, (NeurIPS 2024), 2024

Grigory Malinovsky, Peter Richtárik, Samuel Horváth, Eduard Gorbunov

Federated Optimization Algorithms with Random Reshuffling and Gradient Compression

Published in The Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024), 2024

Abdurakhmon Sadiev, Grigory Malinovsky, Eduard Gorbunov, Igor Sokolov, Ahmed Khaled, Konstantin Burlachenko, Peter Richtárik

MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence

Published in The Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024), 2024

Ionut-Vlad Modoranu, Mher Safaryan, Grigory Malinovsky, Eldar Kurtic, Thomas Robert, Peter Richtarik, Dan Alistarh

Streamlining in the Riemannian Realm: Efficient Riemannian Optimization with Loopless Variance Reduction

Published in arXiv, 2024

Yury Demidovich, Grigory Malinovsky, Peter Richtárik

Minibatch Stochastic Three Points Method for Unconstrained Smooth Minimization

Published in The 38th AAAI Conference on Artificial Intelligence (AAAI 2024), 2024

Soumia Boucherouite, Grigory Malinovsky, Peter Richtárik, El Houcine Bergou

A Guide Through the Zoo of Biased SGD

Published in Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2023), 2023

Yury Demidovich, Grigory Malinovsky, Igor Sokolov, Peter Richtárik

Server-Side Stepsizes and Sampling Without Replacement Provably Help in Federated Optimization

Published in 4th International Workshop on Distributed Machine Learning (DistributedML 2023), 2023

Grigory Malinovsky, Konstantin Mishchenko, Peter Richtárik

MAST: Model-Agnostic Sparsified Training

Published in arXiv, 2023

Yury Demidovich, Grigory Malinovsky, Egor Shulgin, Peter Richtárik

Improving Accelerated Federated Learning with Compression and Importance Sampling

Published in arXiv, 2023

Michał Grudzień, Grigory Malinovsky, Peter Richtárik

TAMUNA: Doubly Accelerated Federated Learning with Local Training, Compression, and Partial Participation

Published in arXiv, 2023

Laurent Condat, Ivan Agarský, Grigory Malinovsky, Peter Richtárik

Federated Learning with Regularized Client Participation

Published in arXiv, 2023

Grigory Malinovsky, Samuel Horváth, Konstantin Burlachenko, Peter Richtárik

An Optimal Algorithm for Strongly Convex Min-min Optimization

Published in arXiv, 2023

Dmitry Kovalev, Alexander Gasnikov, Grigory Malinovsky

Can 5th Generation Local Training Methods Support Client Sampling? Yes!

Published in The 26th International Conference on Artificial Intelligence and Statistics (AISTATS 2023), 2023

Michał Grudzień, Grigory Malinovsky, Peter Richtárik

Random Reshuffling with Variance Reduction: New Analysis and Better Rates

Published in 39th Conference on Uncertainty in Artificial Intelligence (UAI 2023), 2023

Grigory Malinovsky, Alibek Sailanbayev, Peter Richtárik

Variance Reduced ProxSkip: Algorithm, Theory and Application to Federated Learning

Published in Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS 2022), 2022

Grigory Malinovsky, Kai Yi, Peter Richtárik

ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!

Published in Thirty-ninth International Conference on Machine Learning (ICML 2022), 2022

Konstantin Mishchenko, Grigory Malinovsky, Sebastian Stich, Peter Richtárik

Averaged Heavy-Ball Method

Published in Computer Research and Modeling, 2022

Marina Danilova, Grigory Malinovsky

Federated Random Reshuffling with Compression and Variance Reduction

Published in arXiv, 2022

Grigory Malinovsky, Peter Richtárik

Distributed Proximal Splitting Algorithms with Rates and Acceleration

Published in Frontiers in Signal Processing, 2022

Laurent Condat, Grigory Malinovsky, Peter Richtárik

From Local SGD to Local Fixed-Point Methods for Federated Learning

Published in The Thirty-seventh International Conference on Machine Learning (ICML 2020), 2020

Grigory Malinovsky, Dmitry Kovalev, Elnur Gasanov, Laurent Condat, Peter Richtárik