Aleksandr Beznosikov

Comput. Manag. Sci., June, 2024

Decentralized optimization over slowly time-varying graphs: algorithms and lower bounds.

[BibT_eX]

[DOI]

Dmitry Metelev

Anton V. Proskurnikov

Comput. Manag. Sci., June, 2024

Random-reshuffled SARAH does not need full gradient computations.

[BibT_eX]

[DOI]

Martin Takác

Optim. Lett., April, 2024

Optimal Data Splitting in Distributed Optimization for Machine Learning.

[BibT_eX]

[DOI]

Daniil Medyakov

Gleb Molodtsov

CoRR, 2024

Activations and Gradients Compression for Model-Parallel Training.

[BibT_eX]

[DOI]

Mikhail Rudakov

Yaroslav Kholodov

CoRR, 2024

2023

Non-smooth setting of stochastic decentralized convex optimization problem over time-varying Graphs.

[BibT_eX]

[DOI]

Comput. Manag. Sci., December, 2023

Ito Diffusion Approximation of Universal Ito Chains for Sampling, Optimization and Boosting.

[BibT_eX]

[DOI]

Aleksei Ustimenko

CoRR, 2023

Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features.

[BibT_eX]

[DOI]

David Dobre

Gauthier Gidel

CoRR, 2023

Similarity, Compression and Local Steps: Three Pillars of Efficient Communications for Distributed Variational Inequalities.

[BibT_eX]

[DOI]

CoRR, 2023

Real Acceleration of Communication Process in Distributed Algorithms with Compression.

[BibT_eX]

[DOI]

Svetlana Tkachenko

Artem Andreev

Proceedings of the Optimization and Applications - 14th International Conference, 2023

Similarity, Compression and Local Steps: Three Pillars of Efficient Communications for Distributed Variational Inequalities.

[BibT_eX]

[DOI]

Martin Takác

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

First Order Methods with Markovian Noise: from Acceleration to Variational Inequalities.

[BibT_eX]

[DOI]

Sergey Samsonov

Marina Sheshukova

Alexey Naumov

Eric Moulines

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

Stochastic Gradient Descent-Ascent: Unified Theory and New Efficient Methods.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022

Decentralized personalized federated learning: Lower bounds and optimal algorithm for all personalization modes.

[BibT_eX]

[DOI]

EURO J. Comput. Optim., 2022

SARAH-based Variance-reduced Algorithm for Stochastic Finite-sum Cocoercive Variational Inequalities.

[BibT_eX]

[DOI]

CoRR, 2022

Smooth Monotone Stochastic Variational Inequalities and Saddle Point Problems - Survey.

[BibT_eX]

[DOI]

CoRR, 2022

On Scaled Methods for Saddle Point Problems.

[BibT_eX]

[DOI]

CoRR, 2022

Stochastic Gradient Methods with Preconditioned Updates.

[BibT_eX]

[DOI]

Abdulla Jasem Almansoori

Dmitry Kamzolov

Rachael Tappenden

Martin Takác

CoRR, 2022

Optimal Gradient Sliding and its Application to Distributed Optimization Under Similarity.

[BibT_eX]

[DOI]

Ekaterina Borodich

CoRR, 2022

Compression and Data Similarity: Combination of Two Techniques for Communication-Efficient Solving of Distributed Variational Inequalities.

[BibT_eX]

[DOI]

Proceedings of the Optimization and Applications - 13th International Conference, 2022

Optimal Algorithms for Decentralized Stochastic Variational Inequalities.

[BibT_eX]

[DOI]

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

Optimal Gradient Sliding and its Application to Optimal Distributed Optimization Under Similarity.

[BibT_eX]

[DOI]

Ekaterina Borodich

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

Distributed Methods with Compressed Communication for Solving Variational Inequalities, with Theoretical Guarantees.

[BibT_eX]

[DOI]

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

Decentralized Local Stochastic Extra-Gradient for Variational Inequalities.

[BibT_eX]

[DOI]

Anastasia Koloskova

Valentin Samokhin

Sebastian U. Stich

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

The power of first-order smooth optimization for black-box non-smooth problems.

[BibT_eX]

[DOI]

Bin Gu

Proceedings of the International Conference on Machine Learning, 2022

2021

Distributed Saddle-Point Problems Under Similarity.

[BibT_eX]

[DOI]

CoRR, 2021

One-Point Gradient-Free Methods for Composite Optimization with Applications to Distributed Optimization.

[BibT_eX]

[DOI]

Ivan Stepanov

Artyom Voronov

CoRR, 2021

Decentralized Personalized Federated Min-Max Problems.

[BibT_eX]

[DOI]

Vadim Sushko

CoRR, 2021

Decentralized Distributed Optimization for Saddle Point Problems.

[BibT_eX]

[DOI]

CoRR, 2021

Near-Optimal Decentralized Algorithms for Saddle Point Problems over Time-Varying Networks.

[BibT_eX]

[DOI]

Proceedings of the Optimization and Applications - 12th International Conference, 2021

Distributed Saddle-Point Problems Under Data Similarity.

[BibT_eX]

[DOI]

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

One-Point Gradient-Free Methods for Smooth and Non-smooth Saddle-Point Problems.

[BibT_eX]

[DOI]

Vasilii Novitskii

Proceedings of the Mathematical Optimization Theory and Operations Research, 2021

2020

Local SGD for Saddle-Point Problems.

[BibT_eX]

[DOI]

Valentin Samokhin

CoRR, 2020

Zeroth-Order Algorithms for Smooth Saddle-Point Problems.

[BibT_eX]

[DOI]

CoRR, 2020

Gradient-Free Methods for Saddle-Point Problem.

[BibT_eX]

[DOI]