Konstantin Mishchenko

Generating author description...

All published works

Action	Title	Year	Authors
+ PDF Chat	Hardware-Aware Parallel Prompt Decoding for Memory-Efficient Acceleration of LLM Inference	2024	Yang Hao Chen Chen Wayne Luk Ka Fai Cedric Yiu Rui Li Konstantin Mishchenko Stylianos I. Venieris Hongxiang Fan
+ PDF Chat	The Road Less Scheduled	2024	Aaron Defazio Xingyu Yang Harsh Mehta Konstantin Mishchenko Ahmed Khaled Ashok Cutkosky
+ PDF Chat	Super-Universal Regularized Newton Method	2024	Nikita Doikov Konstantin Mishchenko Yurii Nesterov
+	Server-Side Stepsizes and Sampling Without Replacement Provably Help in Federated Optimization	2023	Grigory Malinovsky Konstantin Mishchenko Peter Richtárik
+	Regularized Newton Method with Global ${\boldsymbol{\mathcal{O}(1/{k}^2)}}$ Convergence	2023	Konstantin Mishchenko
+ PDF Chat	Two Losses Are Better Than One: Faster Optimization Using a Cheaper Proxy	2023	Blake Woodworth Konstantin Mishchenko Francis Bach
+	Convergence of First-Order Algorithms for Meta-Learning with Moreau Envelopes	2023	Konstantin Mishchenko Slavomír Hanzely Peter Richtárik
+	Learning-Rate-Free Learning by D-Adaptation	2023	Aaron Defazio Konstantin Mishchenko
+	Two Losses Are Better Than One: Faster Optimization Using a Cheaper Proxy	2023	Blake Woodworth Konstantin Mishchenko Francis Bach
+	DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method	2023	Khaled Ahmed Konstantin Mishchenko Chi Jin
+	Partially Personalized Federated Learning: Breaking the Curse of Data Heterogeneity	2023	Konstantin Mishchenko Rustem Islamov Eduard Gorbunov Samuel Horváth
+	Prodigy: An Expeditiously Adaptive Parameter-Free Learner	2023	Konstantin Mishchenko Aaron Defazio
+	Adaptive Proximal Gradient Method for Convex Optimization	2023	Yura Malitsky Konstantin Mishchenko
+	When, Why and How Much? Adaptive Learning Rate Scheduling by Refinement	2023	Aaron Defazio Ashok Cutkosky Harsh Mehta Konstantin Mishchenko
+ PDF Chat	Dualize, Split, Randomize: Toward Fast Nonsmooth Optimization Algorithms	2022	Adil Salim Laurent Condat Konstantin Mishchenko Peter Richtárik
+	ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!	2022	Konstantin Mishchenko Grigory Malinovsky Sebastian U. Stich Peter Richtárik
+	Server-Side Stepsizes and Sampling Without Replacement Provably Help in Federated Optimization	2022	Grigory Malinovsky Konstantin Mishchenko Peter Richtárik
+	Adaptive Learning Rates for Faster Stochastic Gradient Methods	2022	Samuel Horváth Konstantin Mishchenko Peter Richtárik
+	Super-Universal Regularized Newton Method	2022	Nikita Doikov Konstantin Mishchenko Yurii Nesterov
+	Asynchronous SGD Beats Minibatch SGD Under Arbitrary Delays	2022	Konstantin Mishchenko Francis Bach Mathieu Even Blake Woodworth
+	On Seven Fundamental Optimization Challenges in Machine Learning	2021	Konstantin Mishchenko
+	IntSGD: Floatless Compression of Stochastic Gradients	2021	Konstantin Mishchenko Bokun Wang Dmitry Kovalev Peter Richtárik
+	Proximal and Federated Random Reshuffling	2021	Konstantin Mishchenko Ahmed Khaled Peter Richtárik
+	Regularized Newton Method with Global $O(1/k^2)$ Convergence	2021	Konstantin Mishchenko
+	On Seven Fundamental Optimization Challenges in Machine Learning	2021	Konstantin Mishchenko
+	IntSGD: Adaptive Floatless Compression of Stochastic Gradients	2021	Konstantin Mishchenko Bokun Wang Dmitry Kovalev Peter Richtárik
+	Proximal and Federated Random Reshuffling	2021	Konstantin Mishchenko Khaled Ahmed Peter Richtárik
+	Tighter Theory for Local SGD on Identical and Heterogeneous Data	2020	Ahmed Khaled Konstantin Mishchenko Peter Richtárik
+	Dualize, Split, Randomize: Fast Nonsmooth Optimization Algorithms.	2020	Adil Salim Laurent Condat Konstantin Mishchenko Peter Richtárik
+ PDF Chat	A Distributed Flexible Delay-Tolerant Proximal Gradient Algorithm	2020	Konstantin Mishchenko Franck Iutzeler Jérôme Malick
+	Random Reshuffling: Simple Analysis with Vast Improvements	2020	Konstantin Mishchenko Ahmed Khaled Peter Richtárik
+	Adaptive Gradient Descent without Descent	2019	Yura Malitsky Konstantin Mishchenko
+	Sinkhorn Algorithm as a Special Case of Stochastic Mirror Descent.	2019	Konstantin Mishchenko
+	First Analysis of Local GD on Heterogeneous Data	2019	Ahmed Khaled Konstantin Mishchenko Peter Richtárik
+	Better Communication Complexity for Local SGD	2019	Ahmed Khaled Konstantin Mishchenko Peter Richtárik
+	Tighter Theory for Local SGD on Identical and Heterogeneous Data.	2019	Ahmed Khaled Konstantin Mishchenko Peter Richtárik
+	A Self-supervised Approach to Hierarchical Forecasting with Applications to Groupwise Synthetic Controls.	2019	Konstantin Mishchenko Mallory Montgomery Federico Vaggi
+	A Stochastic Decoupling Method for Minimizing the Sum of Smooth and Non-Smooth Functions	2019	Konstantin Mishchenko Peter Richtárik
+	99% of Distributed Optimization is a Waste of Time: The Issue and How to Fix it	2019	Konstantin Mishchenko Filip Hanzely Peter Richtárik
+	Distributed Learning with Compressed Gradient Differences	2019	Konstantin Mishchenko Eduard Gorbunov Martin Takáč Peter Richtárik
+	Stochastic Distributed Learning with Gradient Quantization and Variance Reduction	2019	Samuel Horváth Dmitry Kovalev Konstantin Mishchenko Sebastian U. Stich Peter Richtárik
+	Revisiting Stochastic Extragradient	2019	Konstantin Mishchenko Dmitry Kovalev Egor Shulgin Peter Richtárik Yura Malitsky
+	MISO is Making a Comeback With Better Proofs and Rates	2019	Xun Qian Alibek Sailanbayev Konstantin Mishchenko Peter Richtárik
+	Stochastic Newton and Cubic Newton Methods with Simple Local Linear-Quadratic Rates	2019	Dmitry Kovalev Konstantin Mishchenko Peter Richtárik
+	Adaptive Gradient Descent without Descent	2019	Konstantin Mishchenko Yura Malitsky
+	Sinkhorn Algorithm as a Special Case of Stochastic Mirror Descent	2019	Konstantin Mishchenko
+	Tighter Theory for Local SGD on Identical and Heterogeneous Data	2019	Ahmed Khaled Konstantin Mishchenko Peter Richtárik
+	First Analysis of Local GD on Heterogeneous Data	2019	Ahmed Khaled Konstantin Mishchenko Peter Richtárik
+	A Self-supervised Approach to Hierarchical Forecasting with Applications to Groupwise Synthetic Controls	2019	Konstantin Mishchenko Mallory Montgomery Federico Vaggi
+	A Stochastic Decoupling Method for Minimizing the Sum of Smooth and Non-Smooth Functions	2019	Konstantin Mishchenko Peter Richtárik
+	99% of Distributed Optimization is a Waste of Time: The Issue and How to Fix it	2019	Konstantin Mishchenko Filip Hanzely Peter Richtárik
+	SEGA: Variance Reduction via Gradient Sketching	2018	Filip Hanzely Konstantin Mishchenko Peter Richtárik
+	A Stochastic Penalty Model for Convex and Nonconvex Optimization with Big Constraints	2018	Konstantin Mishchenko Peter Richtárik

Common Coauthors

Coauthor	Papers Together
Peter Richtárik	29
Ahmed Khaled	7
Dmitry Kovalev	5
Aaron Defazio	4
Yura Malitsky	4
Francis Bach	3
Samuel Horváth	3
Filip Hanzely	3
Grigory Malinovsky	3
Blake Woodworth	3
Federico Vaggi	2
Mallory Montgomery	2
Laurent Condat	2
Adil Salim	2
Sebastian U. Stich	2
Harsh Mehta	2
Ashok Cutkosky	2
Yurii Nesterov	2
Nikita Doikov	2
Eduard Gorbunov	2
Ahmed Khaled	2
Khaled Ahmed	2
Chi Jin	1
Bokun Wang	1
Martin Takáč	1
Ka Fai Cedric Yiu	1
Stylianos I. Venieris	1
Mathieu Even	1
Rustem Islamov	1
Yang	1
Franck Iutzeler	1
Egor Shulgin	1
Xingyu	1
Chen Chen	1
Rui Li	1
Jérôme Malick	1
Slavomír Hanzely	1
Hao	1
Hongxiang Fan	1
Wayne Luk	1
Alibek Sailanbayev	1
Bokun Wang	1
Xun Qian	1

Commonly Cited References

Action	Title	Year	Authors	# of times referenced
+	Proximal-Proximal-Gradient Method	2017	Ernest K. Ryu Wotao Yin	4
+	Variance Reduced Stochastic Gradient Descent with Neighbors	2015	Thomas Hofmann Aurélien Lucchi Simon Lacoste-Julien Brian McWilliams	4
+	Stochastic Quasi-Gradient Methods: Variance Reduction via Jacobian Sketching	2018	Robert M. Gower Peter Richtárik Francis Bach	4
+	Federated Learning: Strategies for Improving Communication Efficiency	2016	Jakub Konečný H. Brendan McMahan Felix X. Yu Peter Richtárik Ananda Theertha Suresh Dave Bacon	4
+	Cubic regularization of Newton method and its global performance	2006	Yurii Nesterov B. T. Polyak	4
+	SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives	2014	Aaron Defazio Francis Bach Simon Lacoste-Julien	4
+	Adding vs. Averaging in Distributed Primal-Dual Optimization	2015	Chenxin Ma Virginia Smith Martin Jaggi Michael I. Jordan Peter Richtárik Martin Takáč	4
+ PDF Chat	Optimization with Sparsity-Inducing Penalties	2011	Francis Bach Rodolphe Jenatton Julien Mairal Guillaume Obozinski	3
+ PDF Chat	Parallel Gradient Distribution in Unconstrained Optimization	1995	L. O. Mangasarian	3
+	Gradient methods for minimizing composite functions	2012	Yu. Nesterov	3
+ PDF Chat	A Descent Lemma Beyond Lipschitz Gradient Continuity: First-Order Methods Revisited and Applications	2016	Heinz H. Bauschke Jérôme Bolte Marc Teboulle	3
+	A Stochastic Decoupling Method for Minimizing the Sum of Smooth and Non-Smooth Functions	2019	Konstantin Mishchenko Peter Richtárik	3
+	A Stochastic Penalty Model for Convex and Nonconvex Optimization with Big Constraints	2018	Konstantin Mishchenko Peter Richtárik	3
+	Lectures on Convex Optimization	2018	Yurii Nesterov	3
+	On the Convergence Properties of a K-step Averaging Stochastic Gradient Descent Algorithm for Nonconvex Optimization	2018	Fan Zhou Guojing Cong	3
+	Introductory Lectures on Convex Optimization: A Basic Course	2014	Ю Е Нестеров	3
+	Finito: A Faster, Permutable Incremental Gradient Method for Big Data Problems	2014	Aaron Defazio Tibério S. Caetano Justin Domke	3
+	A Stochastic Gradient Method with an Exponential Convergence Rate for Finite Training Sets	2012	Nicolas Le Roux Mark Schmidt Francis Bach	3
+ PDF Chat	Surpassing Gradient Descent Provably: A Cyclic Incremental Method with Linear Convergence Rate	2018	Aryan Mokhtari Mert Gürbüzbalaban Alejandro Ribeiro	3
+	Solving variational inequalities with stochastic mirror-prox algorithm	2011	Anatoli Juditsky Arkadi Nemirovski Claire Tauvel	3
+	QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding	2016	Dan Alistarh Demjan Grubic Jerry Li Ryota Tomioka Milan Vojnović	3
+	Total Generalized Variation	2010	Kristian Bredies Karl Kunisch Thomas Pock	3
+	Reducing Noise in GAN Training with Variance Reduced Extragradient	2019	Tatjana Chavdarova Gauthier Gidel François Fleuret Simon Lacoste-Julien	3
+	signSGD: Compressed Optimisation for Non-Convex Problems	2018	Jeremy Bernstein Yu-Xiang Wang Kamyar Azizzadenesheli Animashree Anandkumar	3
+	Distributed Learning with Compressed Gradient Differences	2019	Konstantin Mishchenko Eduard Gorbunov Martin Takáč Peter Richtárik	3
+ PDF Chat	Distributed optimization with arbitrary local solvers	2017	Chenxin Ma Jakub Konečný Martin Jaggi Virginia Smith Michael I. Jordan Peter Richtárik Martin Takáč	3
+	Finito: A Faster, Permutable Incremental Gradient Method for Big Data Problems	2014	Aaron Defazio Justin Domke Tibério S. Caetano	3
+	Stochastic Distributed Learning with Gradient Quantization and Variance Reduction	2019	Samuel Horváth Dmitry Kovalev Konstantin Mishchenko Sebastian U. Stich Peter Richtárik	3
+	Unified Optimal Analysis of the (Stochastic) Gradient Method	2019	Sebastian U. Stich	3
+	Adaptive Federated Learning in Resource Constrained Edge Computing Systems	2018	Shiqiang Wang Tiffany Tuor Theodoros Salonidis Kin K. Leung Christian Makaya Ting He Kevin Chan	2
+ PDF Chat	Implementable tensor methods in unconstrained convex optimization	2019	Yurii Nesterov	2
+	Cooperative SGD: A unified Framework for the Design and Analysis of Communication-Efficient SGD Algorithms	2018	Jianyu Wang Gauri Joshi	2
+ PDF Chat	IQN: An Incremental Quasi-Newton Method with Local Superlinear Convergence Rate	2018	Aryan Mokhtari Mark Eisen Alejandro Ribeiro	2
+	Distributed learning with compressed gradients	2018	Sarit Khirirat Hamid Reza Feyzmahdavian Mikael Johansson	2
+	Sparsified SGD with Memory	2018	Sebastian U. Stich Jean-Baptiste Cordonnier Martin Jaggi	2
+	Stochastic Three-Composite Convex Minimization with a Linear Operator	2018	Renbo Zhao Volkan Cevher	2
+	SVRG meets SAGA: k-SVRG - A Tale of Limited Memory.	2018	Anant Raj Sebastian U. Stich	2
+	Distributed coordinate descent method for learning with big data	2016	Peter Richtárik Martin Takáč	2
+ PDF Chat	Coordinate descent algorithms	2015	Stephen J. Wright	2
+	First-Order Methods in Optimization	2017	Amir Beck	2
+	Randomized projection methods for convex feasibility problems: conditioning and convergence rates	2018	Ion Necoara Peter Richtárik Andrei Pătraşcu	2
+	Local SGD Converges Fast and Communicates Little	2018	Sebastian U. Stich	2
+	A Primal–Dual Splitting Method for Convex Optimization Involving Lipschitzian, Proximable and Linear Composite Terms	2012	Laurent Condat	2
+	Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite-Sum Structure	2016	Alberto Bietti Julien Mairal	2
+ PDF Chat	Relatively Smooth Convex Optimization by First-Order Methods, and Applications	2018	Haihao Lu Robert M. Freund Yurii Nesterov	2
+	A method for the solution of certain non-linear problems in least squares	1944	Kenneth Levenberg	2
+ PDF Chat	On the ergodic convergence rates of a first-order primal–dual algorithm	2015	Antonin Chambolle Thomas Pock	2
+	AIDE: Fast and Communication Efficient Distributed Optimization	2016	Sashank J. Reddi Jakub Konečný Peter Richtárik Barnabás Póczos Alexander J. Smola	2
+ PDF Chat	Stochastic gradient descent, weighted sampling, and the randomized Kaczmarz algorithm	2015	Deanna Needell Nathan Srebro Rachel Ward	2
+ PDF Chat	Adaptive cubic regularisation methods for unconstrained optimization. Part I: motivation, convergence and numerical results	2009	Coralia Cartis Nicholas I. M. Gould Philippe L. Toint	2