Takip et
Grigory Malinovsky
Grigory Malinovsky
PhD student, King Abdullah University of Science and Technology
kaust.edu.sa üzerinde doğrulanmış e-posta adresine sahip - Ana Sayfa
Başlık
Alıntı yapanlar
Alıntı yapanlar
Yıl
Proxskip: Yes! local gradient steps provably lead to communication acceleration! finally!
K Mishchenko, G Malinovsky, S Stich, P Richtárik
International Conference on Machine Learning, 15750-15769, 2022
1772022
From local SGD to local fixed-point methods for federated learning
G Malinovskiy, D Kovalev, E Gasanov, L Condat, P Richtarik
International Conference on Machine Learning, 6692-6701, 2020
1482020
A guide through the zoo of biased SGD
Y Demidovich, G Malinovsky, I Sokolov, P Richtárik
Advances in Neural Information Processing Systems 36, 23158-23171, 2023
372023
Variance reduced proxskip: Algorithm, theory and application to federated learning
G Malinovsky, K Yi, P Richtárik
Advances in Neural Information Processing Systems 35, 15176-15189, 2022
372022
Don't Compress Gradients in Random Reshuffling: Compress Gradient Differences
A Sadiev, G Malinovsky, E Gorbunov, I Sokolov, A Khaled, K Burlachenko, ...
NeurIPS 2024, 2024
29*2024
Can 5th generation local training methods support client sampling? yes!
M Grudzień, G Malinovsky, P Richtárik
International Conference on Artificial Intelligence and Statistics, 1055-1092, 2023
292023
Server-side stepsizes and sampling without replacement provably help in federated optimization
G Malinovsky, K Mishchenko, P Richtárik
Proceedings of the 4th International Workshop on Distributed Machine …, 2023
282023
Distributed proximal splitting algorithms with rates and acceleration
L Condat, G Malinovsky, P Richtárik
Frontiers in Signal Processing 1, 776825, 2022
242022
Random reshuffling with variance reduction: New analysis and better rates
G Malinovsky, A Sailanbayev, P Richtárik
Uncertainty in Artificial Intelligence, 1347-1357, 2023
232023
TAMUNA: Doubly accelerated distributed optimization with local training, compression, and partial participation
L Condat, I Agarský, G Malinovsky, P Richtárik
arXiv preprint arXiv:2302.09832, 2023
19*2023
Federated learning with regularized client participation
G Malinovsky, S Horváth, K Burlachenko, P Richtárik
arXiv preprint arXiv:2302.03662, 2023
182023
Improving accelerated federated learning with compression and importance sampling
M Grudzień, G Malinovsky, P Richtárik
arXiv preprint arXiv:2306.03240, 2023
152023
Byzantine Robustness and Partial Participation Can Be Achieved at Once: Just Clip Gradient Differences
G Malinovsky, P Richtárik, S Horváth, E Gorbunov
Advances in Neural Information Processing Systems 37, 34900-34979, 2025
102025
Microadam: Accurate adaptive optimization with low space overhead and provable convergence
IV Modoranu, M Safaryan, G Malinovsky, E Kurtić, T Robert, P Richtarik, ...
Advances in Neural Information Processing Systems 37, 1-43, 2024
9*2024
Federated random reshuffling with compression and variance reduction
G Malinovsky, P Richtárik
arXiv preprint arXiv:2205.03914, 2022
82022
An optimal algorithm for strongly convex min-min optimization
A Gasnikov, D Kovalev, G Malinovsky
arXiv preprint arXiv:2212.14439, 2022
72022
Minibatch stochastic three points method for unconstrained smooth minimization
S Boucherouite, G Malinovsky, P Richtárik, EH Bergou
Proceedings of the AAAI Conference on Artificial Intelligence 38 (18), 20344 …, 2024
52024
Averaged heavy-ball method Метод тяжелого шарика с усреднением
MY Danilova, GS Malinovsky
Izhevsk Institute of Computer Science, 2022
5*2022
Randomized asymmetric chain of lora: The first meaningful theoretical framework for low-rank adaptation
G Malinovsky, U Michieli, HAAK Hammoud, T Ceritli, H Elesedy, M Ozay, ...
arXiv preprint arXiv:2410.08305, 2024
32024
Methods with local steps and random reshuffling for generally smooth non-convex federated optimization
Y Demidovich, P Ostroukhov, G Malinovsky, S Horváth, M Takáč, ...
arXiv preprint arXiv:2412.02781, 2024
22024
Sistem, işlemi şu anda gerçekleştiremiyor. Daha sonra yeniden deneyin.
Makaleler 1–20