Konstantin Mishchenko

According to our database, Konstantin Mishchenko authored at least 39 papers between 2018 and 2024.

Collaborative distances:

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

2024

Super-Universal Regularized Newton Method.

Nikita Doikov, Konstantin Mishchenko, Yurii E. Nesterov

SIAM J. Optim., March, 2024

Hardware-Aware Parallel Prompt Decoding for Memory-Efficient Acceleration of LLM Inference.

Hao Mark Chen, Wayne Luk, Ka Fai Cedric Yiu, Rui Li, Konstantin Mishchenko, Stylianos I. Venieris, Hongxiang Fan

CoRR, 2024

The Road Less Scheduled.

Aaron Defazio, Xingyu Yang, Harsh Mehta, Konstantin Mishchenko, Ahmed Khaled, Ashok Cutkosky

CoRR, 2024

Prodigy: An Expeditiously Adaptive Parameter-Free Learner.

Konstantin Mishchenko, Aaron Defazio

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

Regularized Newton Method with Global \({\boldsymbol{\mathcal{O}(1/{k}^2)}}\) Convergence.

Konstantin Mishchenko

SIAM J. Optim., September, 2023

Stochastic distributed learning with gradient quantization and double-variance reduction.

Samuel Horváth, Dmitry Kovalev, Konstantin Mishchenko, Peter Richtárik, Sebastian U. Stich

Optim. Methods Softw., January, 2023

When, Why and How Much? Adaptive Learning Rate Scheduling by Refinement.

Aaron Defazio, Ashok Cutkosky, Harsh Mehta, Konstantin Mishchenko

CoRR, 2023

Adaptive Proximal Gradient Method for Convex Optimization.

Yura Malitsky, Konstantin Mishchenko

CoRR, 2023

Partially Personalized Federated Learning: Breaking the Curse of Data Heterogeneity.

Konstantin Mishchenko, Rustem Islamov, Eduard Gorbunov, Samuel Horváth

CoRR, 2023

Convergence of First-Order Algorithms for Meta-Learning with Moreau Envelopes.

Konstantin Mishchenko, Slavomír Hanzely, Peter Richtárik

CoRR, 2023

DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method.

Ahmed Khaled, Konstantin Mishchenko, Chi Jin

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

Two Losses Are Better Than One: Faster Optimization Using a Cheaper Proxy.

Blake E. Woodworth, Konstantin Mishchenko, Francis R. Bach

Proceedings of the International Conference on Machine Learning, 2023

Learning-Rate-Free Learning by D-Adaptation.

Aaron Defazio, Konstantin Mishchenko

Proceedings of the International Conference on Machine Learning, 2023

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

Grigory Malinovsky, Konstantin Mishchenko, Peter Richtárik

Proceedings of the 4th International Workshop on Distributed Machine Learning, 2023

2022

Dualize, Split, Randomize: Toward Fast Nonsmooth Optimization Algorithms.

Adil Salim, Laurent Condat, Konstantin Mishchenko, Peter Richtárik

J. Optim. Theory Appl., 2022

Adaptive Learning Rates for Faster Stochastic Gradient Methods.

Samuel Horváth, Konstantin Mishchenko, Peter Richtárik

CoRR, 2022

Asynchronous SGD Beats Minibatch SGD Under Arbitrary Delays.

Konstantin Mishchenko, Francis R. Bach, Mathieu Even, Blake E. Woodworth

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

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

Konstantin Mishchenko, Grigory Malinovsky, Sebastian U. Stich, Peter Richtárik

Proceedings of the International Conference on Machine Learning, 2022

Proximal and Federated Random Reshuffling.

Konstantin Mishchenko, Ahmed Khaled, Peter Richtárik

Proceedings of the International Conference on Machine Learning, 2022

IntSGD: Adaptive Floatless Compression of Stochastic Gradients.

Konstantin Mishchenko, Bokun Wang, Dmitry Kovalev, Peter Richtárik

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Regularized Newton Method with Global O(1/k²) Convergence.

Konstantin Mishchenko

CoRR, 2021

IntSGD: Floatless Compression of Stochastic Gradients.

Konstantin Mishchenko, Bokun Wang, Dmitry Kovalev, Peter Richtárik

CoRR, 2021

2020

A Distributed Flexible Delay-Tolerant Proximal Gradient Algorithm.

Konstantin Mishchenko, Franck Iutzeler, Jérôme Malick

SIAM J. Optim., 2020

Dualize, Split, Randomize: Fast Nonsmooth Optimization Algorithms.

Adil Salim, Laurent Condat, Konstantin Mishchenko, Peter Richtárik

CoRR, 2020

99% of Worker-Master Communication in Distributed Optimization Is Not Needed.

Konstantin Mishchenko, Filip Hanzely, Peter Richtárik

Proceedings of the Thirty-Sixth Conference on Uncertainty in Artificial Intelligence, 2020

Random Reshuffling: Simple Analysis with Vast Improvements.

Konstantin Mishchenko, Ahmed Khaled, Peter Richtárik

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Adaptive Gradient Descent without Descent.

Yura Malitsky, Konstantin Mishchenko

Proceedings of the 37th International Conference on Machine Learning, 2020

DAve-QN: A Distributed Averaged Quasi-Newton Method with Local Superlinear Convergence Rate.

Saeed Soori, Konstantin Mishchenko, Aryan Mokhtari, Maryam Mehri Dehnavi, Mert Gürbüzbalaban

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

Revisiting Stochastic Extragradient.

Konstantin Mishchenko, Dmitry Kovalev, Egor Shulgin, Peter Richtárik, Yura Malitsky

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

Tighter Theory for Local SGD on Identical and Heterogeneous Data.

Ahmed Khaled, Konstantin Mishchenko, Peter Richtárik

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

2019

Stochastic Newton and Cubic Newton Methods with Simple Local Linear-Quadratic Rates.

Dmitry Kovalev, Konstantin Mishchenko, Peter Richtárik

CoRR, 2019

Sinkhorn Algorithm as a Special Case of Stochastic Mirror Descent.

Konstantin Mishchenko

CoRR, 2019

Better Communication Complexity for Local SGD.

Ahmed Khaled, Konstantin Mishchenko, Peter Richtárik

CoRR, 2019

First Analysis of Local GD on Heterogeneous Data.

Ahmed Khaled, Konstantin Mishchenko, Peter Richtárik

CoRR, 2019

A Self-supervised Approach to Hierarchical Forecasting with Applications to Groupwise Synthetic Controls.

Konstantin Mishchenko, Mallory Montgomery, Federico Vaggi

CoRR, 2019

99% of Parallel Optimization is Inevitably a Waste of Time.

Konstantin Mishchenko, Filip Hanzely, Peter Richtárik

CoRR, 2019

Distributed Learning with Compressed Gradient Differences.

Konstantin Mishchenko, Eduard Gorbunov, Martin Takác, Peter Richtárik

CoRR, 2019

2018

SEGA: Variance Reduction via Gradient Sketching.

Filip Hanzely, Konstantin Mishchenko, Peter Richtárik

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

A Delay-tolerant Proximal-Gradient Algorithm for Distributed Learning.

Konstantin Mishchenko, Franck Iutzeler, Jérôme Malick, Massih-Reza Amini

Proceedings of the 35th International Conference on Machine Learning, 2018