Peter Richtárik

I'm a Professor of Machine Learning at KAUST (King Abdullah University of Science and Technology), where I develop mathematical and algorithmic foundations of machine learning. My current research focuses on optimization methods for massive-scale machine learning problems and federated learning.

I work extensively on distributed optimization and machine learning algorithms, including compressed training, variance reduction, stochastic gradient descent, and federated learning approaches. Prior to KAUST, I held research positions at the University of Edinburgh, where I helped advance core algorithms like coordinate descent and developed communication-efficient methods for distributed training.

My work aims to bridge theory and practice in large-scale machine learning. I'm particularly interested in developing algorithms that can efficiently train machine learning models across distributed systems while minimizing communication overhead. Recently, I've focused significantly on federated learning, developing new techniques that enable efficient distributed training on edge devices.

Publications

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

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

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

arXiv.org 2024

PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression

PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression

Vladimir Malinovskii, Denis Mazur, Ivan Ilin, Denis Kuznedelev, Konstantin Burlachenko, Kai Yi, Dan Alistarh, Peter Richtárik

arXiv.org 2024

Consensus-based optimisation with truncated noise

Massimo Fornasier, Peter Richtárik, Konstantin Riedl, Lukang Sun

European journal of applied mathematics 2024

Kimad: Adaptive Gradient Compression with Bandwidth Awareness

Kimad: Adaptive Gradient Compression with Bandwidth Awareness

Jihao Xin, Ivan Ilin, Shunkang Zhang, Marco Canini, Peter Richtárik

DistributedML@CoNEXT 2023

Federated Learning is Better with Non-Homomorphic Encryption

Federated Learning is Better with Non-Homomorphic Encryption

Konstantin Burlachenko, Abdulmajeed Alrowithi, Fahad Albalawi, Peter Richtárik

DistributedML@CoNEXT 2023

Understanding Progressive Training Through the Framework of Randomized Coordinate Descent

Understanding Progressive Training Through the Framework of Randomized Coordinate Descent

Rafal Szlendak, Elnur Gasanov, Peter Richtárik

International Conference on Artificial Intelligence and Statistics 2023

A Guide Through the Zoo of Biased SGD

A Guide Through the Zoo of Biased SGD

Y. Demidovich, Grigory Malinovsky, Igor Sokolov, Peter Richtárik

Neural Information Processing Systems 2023

Det-CGD: Compressed Gradient Descent with Matrix Stepsizes for Non-Convex Optimization

Det-CGD: Compressed Gradient Descent with Matrix Stepsizes for Non-Convex Optimization

Hanmin Li, Avetik G. Karagulyan, Peter Richtárik

International Conference on Learning Representations 2023

Optimal Time Complexities of Parallel Stochastic Optimization Methods Under a Fixed Computation Model

Optimal Time Complexities of Parallel Stochastic Optimization Methods Under a Fixed Computation Model

Alexander Tyurin, Peter Richtárik

Neural Information Processing Systems 2023

High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance

High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance

Abdurakhmon Sadiev, Marina Danilova, Eduard A. Gorbunov, Samuel Horváth, Gauthier Gidel, P. Dvurechensky, A. Gasnikov, Peter Richtárik

International Conference on Machine Learning 2023

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

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

Konstantin Mishchenko, Slavomír Hanzely, Peter Richtárik

arXiv.org 2023

A Damped Newton Method Achieves Global $O\left(\frac{1}{k^2}\right)$ and Local Quadratic Convergence Rate

A Damped Newton Method Achieves Global $O\left(\frac{1}{k^2}\right)$ and Local Quadratic Convergence Rate

Slavomír Hanzely, D. Kamzolov, D. Pasechnyuk, Alexander Gasnikov, Peter Richtárik, Martin Takávč

Adaptive Compression for Communication-Efficient Distributed Training

Adaptive Compression for Communication-Efficient Distributed Training

Maksim Makarenko, Elnur Gasanov, Rustem Islamov, Abdurakhmon Sadiev, Peter Richtárik

Trans. Mach. Learn. Res. 2022

Improved Stein Variational Gradient Descent with Importance Weights

Improved Stein Variational Gradient Descent with Importance Weights

Lukang Sun, Peter Richtárik

arXiv.org 2022

Stochastic distributed learning with gradient quantization and double-variance reduction

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

Optim. Methods Softw. 2022

Minibatch Stochastic Three Points Method for Unconstrained Smooth Minimization

Minibatch Stochastic Three Points Method for Unconstrained Smooth Minimization

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

AAAI Conference on Artificial Intelligence 2022

Adaptive Learning Rates for Faster Stochastic Gradient Methods

Adaptive Learning Rates for Faster Stochastic Gradient Methods

Samuel Horváth, Konstantin Mishchenko, Peter Richtárik

arXiv.org 2022

RandProx: Primal-Dual Optimization Algorithms with Randomized Proximal Updates

RandProx: Primal-Dual Optimization Algorithms with Randomized Proximal Updates

Laurent Condat, Peter Richtárik

International Conference on Learning Representations 2022

Communication Acceleration of Local Gradient Methods via an Accelerated Primal-Dual Algorithm with Inexact Prox

Communication Acceleration of Local Gradient Methods via an Accelerated Primal-Dual Algorithm with Inexact Prox

Abdurakhmon Sadiev, Dmitry Kovalev, Peter Richtárik

Neural Information Processing Systems 2022

A Note on the Convergence of Mirrored Stein Variational Gradient Descent under (L0, L1)-Smoothness Condition

Lukang Sun, Peter Richtárik

arXiv.org 2022

Convergence of Stein Variational Gradient Descent under a Weaker Smoothness Condition

Convergence of Stein Variational Gradient Descent under a Weaker Smoothness Condition

Lukang Sun, Avetik Karagulyan, Peter Richtárik

International Conference on Artificial Intelligence and Statistics 2022

Federated Random Reshuffling with Compression and Variance Reduction

Federated Random Reshuffling with Compression and Variance Reduction

Grigory Malinovsky, Peter Richtárik

arXiv.org 2022

Optimal Algorithms for Decentralized Stochastic Variational Inequalities

Optimal Algorithms for Decentralized Stochastic Variational Inequalities

Dmitry Kovalev, Aleksandr Beznosikov, Abdurakhmon Sadiev, Michael Persiianov, Peter Richtárik, A. Gasnikov

Neural Information Processing Systems 2022

Accelerated Primal-Dual Gradient Method for Smooth and Convex-Concave Saddle-Point Problems with Bilinear Coupling

Accelerated Primal-Dual Gradient Method for Smooth and Convex-Concave Saddle-Point Problems with Bilinear Coupling

Dmitry Kovalev, Alexander Gasnikov, Peter Richtárik

Neural Information Processing Systems 2021

Faster Rates for Compressed Federated Learning with Client-Variance Reduction

Faster Rates for Compressed Federated Learning with Client-Variance Reduction

Haoyu Zhao, Konstantin Burlachenko, Zhize Li, Peter Richtárik

SIAM Journal on Mathematics of Data Science 2021

FL_PyTorch: optimization research simulator for federated learning

FL_PyTorch: optimization research simulator for federated learning

Konstantin Burlachenko, Samuel Horváth, Peter Richtárik

DistributedML@CoNEXT 2021

EF21 with Bells & Whistles: Practical Algorithmic Extensions of Modern Error Feedback

EF21 with Bells & Whistles: Practical Algorithmic Extensions of Modern Error Feedback

Ilyas Fatkhullin, Igor Sokolov, Eduard Gorbunov, Zhize Li, Peter Richtárik

arXiv.org 2021

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

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

Aleksandr Beznosikov, Peter Richtárik, Michael Diskin, Max Ryabinin, A. Gasnikov

Neural Information Processing Systems 2021

Permutation Compressors for Provably Faster Distributed Nonconvex Optimization

Permutation Compressors for Provably Faster Distributed Nonconvex Optimization

Rafal Szlendak, Alexander Tyurin, Peter Richtárik

arXiv.org 2021

Error Compensated Loopless SVRG, Quartz, and SDCA for Distributed Optimization

Error Compensated Loopless SVRG, Quartz, and SDCA for Distributed Optimization

Xun Qian, Hanze Dong, Peter Richtárik, Tong Zhang

Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information

Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information

Majid Jahani, S. Rusakov, Zheng Shi, Peter Richtárik, Michael W. Mahoney, Martin Tak'avc

International Conference on Learning Representations 2021

FedPAGE: A Fast Local Stochastic Gradient Method for Communication-Efficient Federated Learning

FedPAGE: A Fast Local Stochastic Gradient Method for Communication-Efficient Federated Learning

Haoyu Zhao, Zhize Li, Peter Richtárik

arXiv.org 2021

CANITA: Faster Rates for Distributed Convex Optimization with Communication Compression

CANITA: Faster Rates for Distributed Convex Optimization with Communication Compression

Zhize Li, Peter Richtárik

Neural Information Processing Systems 2021

A Field Guide to Federated Optimization

A Field Guide to Federated Optimization

Jianyu Wang, Zachary B. Charles, Zheng Xu, Gauri Joshi, H. B. McMahan, B. A. Y. Arcas, Maruan Al-Shedivat, Galen Andrew, S. Avestimehr, Katharine Daly, Deepesh Data, S. Diggavi, Hubert Eichner, Advait Gadhikar, Zachary Garrett, Antonious M. Girgis, Filip Hanzely, Andrew Straiton Hard, Chaoyang He, Samuel Horváth, Zhouyuan Huo, A. Ingerman, Martin Jaggi, T. Javidi, P. Kairouz, Satyen Kale, Sai Praneeth Karimireddy, Jakub Konecný, Sanmi Koyejo, Tian Li, Luyang Liu, M. Mohri, H. Qi, Sashank J. Reddi, Peter Richtárik, K. Singhal, Virginia Smith, M. Soltanolkotabi, Weikang Song, A. Suresh, Sebastian U. Stich, Ameet Talwalkar, Hongyi Wang, Blake E. Woodworth, Shanshan Wu, Felix X. Yu, Honglin Yuan, M. Zaheer, Mi Zhang, Tong Zhang, Chunxiang Zheng, Chen Zhu, Wennan Zhu

arXiv.org 2021

EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback

EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback

Peter Richtárik, Igor Sokolov, Ilyas Fatkhullin

Neural Information Processing Systems 2021

Lower Bounds and Optimal Algorithms for Smooth and Strongly Convex Decentralized Optimization Over Time-Varying Networks

Lower Bounds and Optimal Algorithms for Smooth and Strongly Convex Decentralized Optimization Over Time-Varying Networks

Dmitry Kovalev, Elnur Gasanov, Peter Richtárik, Alexander Gasnikov

Neural Information Processing Systems 2021

A Convergence Theory for SVGD in the Population Limit under Talagrand's Inequality T1

Adil Salim, Lukang Sun, Peter Richtárik

International Conference on Machine Learning 2021

MURANA: A Generic Framework for Stochastic Variance-Reduced Optimization

MURANA: A Generic Framework for Stochastic Variance-Reduced Optimization

Laurent Condat, Peter Richtárik

Mathematical and Scientific Machine Learning 2021

FedNL: Making Newton-Type Methods Applicable to Federated Learning

FedNL: Making Newton-Type Methods Applicable to Federated Learning

Mher Safaryan, Rustem Islamov, Xun Qian, Peter Richtárik

International Conference on Machine Learning 2021

Random Reshuffling with Variance Reduction: New Analysis and Better Rates

Grigory Malinovsky, Alibek Sailanbayev, Peter Richtárik

Conference on Uncertainty in Artificial Intelligence 2021

ZeroSARAH: Efficient Nonconvex Finite-Sum Optimization with Zero Full Gradient Computation

ZeroSARAH: Efficient Nonconvex Finite-Sum Optimization with Zero Full Gradient Computation

Zhize Li, Peter Richtárik

arXiv.org 2021

Hyperparameter Transfer Learning with Adaptive Complexity

Hyperparameter Transfer Learning with Adaptive Complexity

Samuel Horváth, Aaron Klein, Peter Richtárik, C. Archambeau

International Conference on Artificial Intelligence and Statistics 2021

An Optimal Algorithm for Strongly Convex Minimization under Affine Constraints

An Optimal Algorithm for Strongly Convex Minimization under Affine Constraints

A. Salim, Laurent Condat, D. Kovalev, Peter Richtárik

International Conference on Artificial Intelligence and Statistics 2021

AI-SARAH: Adaptive and Implicit Stochastic Recursive Gradient Methods

Zheng Shi, Nicolas Loizou, Peter Richtárik, Martin Tak'avc

Trans. Mach. Learn. Res. 2021

ADOM: Accelerated Decentralized Optimization Method for Time-Varying Networks

ADOM: Accelerated Decentralized Optimization Method for Time-Varying Networks

D. Kovalev, Egor Shulgin, Peter Richtárik, A. Rogozin, A. Gasnikov

International Conference on Machine Learning 2021

IntSGD: Adaptive Floatless Compression of Stochastic Gradients

IntSGD: Adaptive Floatless Compression of Stochastic Gradients

Konstantin Mishchenko, Bokun Wang, D. Kovalev, Peter Richtárik

International Conference on Learning Representations 2021

MARINA: Faster Non-Convex Distributed Learning with Compression

MARINA: Faster Non-Convex Distributed Learning with Compression

Eduard A. Gorbunov, Konstantin Burlachenko, Zhize Li, Peter Richtárik

International Conference on Machine Learning 2021

Smoothness Matrices Beat Smoothness Constants: Better Communication Compression Techniques for Distributed Optimization

Smoothness Matrices Beat Smoothness Constants: Better Communication Compression Techniques for Distributed Optimization

Mher Safaryan, Filip Hanzely, Peter Richtárik

Neural Information Processing Systems 2021

Distributed Second Order Methods with Fast Rates and Compressed Communication

Distributed Second Order Methods with Fast Rates and Compressed Communication

R. Islamov, Xun Qian, Peter Richtárik

International Conference on Machine Learning 2021

Proximal and Federated Random Reshuffling

Proximal and Federated Random Reshuffling

Konstantin Mishchenko, Ahmed Khaled, Peter Richtárik

International Conference on Machine Learning 2021

A Linearly Convergent Algorithm for Decentralized Optimization: Sending Less Bits for Free!

A Linearly Convergent Algorithm for Decentralized Optimization: Sending Less Bits for Free!

D. Kovalev, Anastasia Koloskova, Martin Jaggi, Peter Richtárik, Sebastian U. Stich

International Conference on Artificial Intelligence and Statistics 2020

Local SGD: Unified Theory and New Efficient Methods

Local SGD: Unified Theory and New Efficient Methods

Eduard A. Gorbunov, Filip Hanzely, Peter Richtárik

International Conference on Artificial Intelligence and Statistics 2020

Optimal Client Sampling for Federated Learning

Optimal Client Sampling for Federated Learning

Wenlin Chen, Samuel Horváth, Peter Richtárik

Trans. Mach. Learn. Res. 2020

Linearly Converging Error Compensated SGD

Linearly Converging Error Compensated SGD

Eduard A. Gorbunov, D. Kovalev, Dmitry Makarenko, Peter Richtárik

Neural Information Processing Systems 2020

Optimal Gradient Compression for Distributed and Federated Learning

Optimal Gradient Compression for Distributed and Federated Learning

Alyazeed Albasyoni, Mher Safaryan, Laurent Condat, Peter Richtárik

arXiv.org 2020

Lower Bounds and Optimal Algorithms for Personalized Federated Learning

Lower Bounds and Optimal Algorithms for Personalized Federated Learning

Filip Hanzely, Slavomír Hanzely, Samuel Horváth, Peter Richtárik

Neural Information Processing Systems 2020

Distributed Proximal Splitting Algorithms with Rates and Acceleration

Distributed Proximal Splitting Algorithms with Rates and Acceleration

Laurent Condat, Grigory Malinovsky, Peter Richtárik

Frontiers in Signal Processing 2020

Variance-Reduced Methods for Machine Learning

Variance-Reduced Methods for Machine Learning

Robert Mansel Gower, Mark W. Schmidt, F. Bach, Peter Richtárik

Proceedings of the IEEE 2020

Error Compensated Distributed SGD Can Be Accelerated

Error Compensated Distributed SGD Can Be Accelerated

Xun Qian, Peter Richtárik, Tong Zhang

Neural Information Processing Systems 2020

PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization

PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization

Zhize Li, Hongyan Bao, Xiangliang Zhang, Peter Richtárik

International Conference on Machine Learning 2020

Acceleration for Compressed Gradient Descent in Distributed Optimization

Zhize Li, D. Kovalev, Xun Qian, Peter Richtárik

International Conference on Machine Learning 2020

Optimal and Practical Algorithms for Smooth and Strongly Convex Decentralized Optimization

Optimal and Practical Algorithms for Smooth and Strongly Convex Decentralized Optimization

D. Kovalev, A. Salim, Peter Richtárik

Neural Information Processing Systems 2020

Unified Analysis of Stochastic Gradient Methods for Composite Convex and Smooth Optimization

Ahmed Khaled, Othmane Sebbouh, Nicolas Loizou, R. Gower, Peter Richtárik

Journal of Optimization Theory and Applications 2020

A Better Alternative to Error Feedback for Communication-Efficient Distributed Learning

A Better Alternative to Error Feedback for Communication-Efficient Distributed Learning

Samuel Horváth, Peter Richtárik

International Conference on Learning Representations 2020

Primal Dual Interpretation of the Proximal Stochastic Gradient Langevin Algorithm

Primal Dual Interpretation of the Proximal Stochastic Gradient Langevin Algorithm

A. Salim, Peter Richtárik

Neural Information Processing Systems 2020

A Unified Analysis of Stochastic Gradient Methods for Nonconvex Federated Optimization

A Unified Analysis of Stochastic Gradient Methods for Nonconvex Federated Optimization

Zhize Li, Peter Richtárik

arXiv.org 2020

Random Reshuffling: Simple Analysis with Vast Improvements

Random Reshuffling: Simple Analysis with Vast Improvements

Konstantin Mishchenko, Ahmed Khaled, Peter Richtárik

Neural Information Processing Systems 2020

Adaptive Learning of the Optimal Mini-Batch Size of SGD

Adaptive Learning of the Optimal Mini-Batch Size of SGD

Motasem Alfarra, Slavomír Hanzely, Alyazeed Albasyoni, Bernard Ghanem, Peter Richtárik

arXiv.org 2020

On the Convergence Analysis of Asynchronous SGD for Solving Consistent Linear Systems

On the Convergence Analysis of Asynchronous SGD for Solving Consistent Linear Systems

Atal Narayan Sahu, Aritra Dutta, Aashutosh Tiwari, Peter Richtárik

Linear Algebra and its Applications 2020

Dualize, Split, Randomize: Fast Nonsmooth Optimization Algorithms

Dualize, Split, Randomize: Fast Nonsmooth Optimization Algorithms

A. Salim, Laurent Condat, Konstantin Mishchenko, Peter Richtárik

arXiv.org 2020

From Local SGD to Local Fixed Point Methods for Federated Learning

From Local SGD to Local Fixed Point Methods for Federated Learning

Grigory Malinovsky, D. Kovalev, Elnur Gasanov, Laurent Condat, Peter Richtárik

International Conference on Machine Learning 2020

Dualize, Split, Randomize: Toward Fast Nonsmooth Optimization Algorithms

A. Salim, Laurent Condat, Konstantin Mishchenko, Peter Richtárik

Journal of Optimization Theory and Applications 2020

On Biased Compression for Distributed Learning

On Biased Compression for Distributed Learning

Aleksandr Beznosikov, Samuel Horvath, Peter Richtárik, Mher Safaryan

Journal of machine learning research 2020

Fast Linear Convergence of Randomized BFGS

Fast Linear Convergence of Randomized BFGS

D. Kovalev, Robert Mansel Gower, Peter Richtárik, A. Rogozin

arXiv.org 2020

Acceleration for Compressed Gradient Descent in Distributed and Federated Optimization

Acceleration for Compressed Gradient Descent in Distributed and Federated Optimization

Zhize Li, D. Kovalev, Xun Qian, Peter Richtárik

International Conference on Machine Learning 2020

Stochastic Subspace Cubic Newton Method

Stochastic Subspace Cubic Newton Method

Filip Hanzely, N. Doikov, Peter Richtárik, Y. Nesterov

International Conference on Machine Learning 2020

Uncertainty Principle for Communication Compression in Distributed and Federated Learning and the Search for an Optimal Compressor

Uncertainty Principle for Communication Compression in Distributed and Federated Learning and the Search for an Optimal Compressor

Mher Safaryan, Egor Shulgin, Peter Richtárik

Information and Inference A Journal of the IMA 2020

Adaptivity of Stochastic Gradient Methods for Nonconvex Optimization

Adaptivity of Stochastic Gradient Methods for Nonconvex Optimization

Samuel Horváth, Lihua Lei, Peter Richtárik, Michael I. Jordan

SIAM Journal on Mathematics of Data Science 2020

Variance Reduced Coordinate Descent with Acceleration: New Method With a Surprising Application to Finite-Sum Problems

Variance Reduced Coordinate Descent with Acceleration: New Method With a Surprising Application to Finite-Sum Problems

Filip Hanzely, D. Kovalev, Peter Richtárik

International Conference on Machine Learning 2020

Federated Learning of a Mixture of Global and Local Models

Federated Learning of a Mixture of Global and Local Models

Filip Hanzely, Peter Richtárik

arXiv.org 2020

Better Theory for SGD in the Nonconvex World

Better Theory for SGD in the Nonconvex World

Ahmed Khaled, Peter Richtárik

Trans. Mach. Learn. Res. 2020

Distributed Fixed Point Methods with Compressed Iterates

S'elim Chraibi, Ahmed Khaled, D. Kovalev, Peter Richtárik, A. Salim, Martin Tak'avc

arXiv.org 2019

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

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

D. Kovalev, Konstantin Mishchenko, Peter Richtárik

arXiv.org 2019

Gradient Descent with Compressed Iterates

Gradient Descent with Compressed Iterates

Ahmed Khaled, Peter Richtárik

arXiv.org 2019

Tighter Theory for Local SGD on Identical and Heterogeneous Data

Tighter Theory for Local SGD on Identical and Heterogeneous Data

Ahmed Khaled, Konstantin Mishchenko, Peter Richtárik

International Conference on Artificial Intelligence and Statistics 2019

First Analysis of Local GD on Heterogeneous Data

First Analysis of Local GD on Heterogeneous Data

Ahmed Khaled, Konstantin Mishchenko, Peter Richtárik

arXiv.org 2019

Better Communication Complexity for Local SGD

Better Communication Complexity for Local SGD

Ahmed Khaled, Konstantin Mishchenko, Peter Richtárik

arXiv.org 2019

Stochastic Convolutional Sparse Coding

Stochastic Convolutional Sparse Coding

J. Xiong, Peter Richtárik, W. Heidrich

International Symposium on Vision, Modeling, and Visualization 2019

MISO is Making a Comeback With Better Proofs and Rates

MISO is Making a Comeback With Better Proofs and Rates

Xun Qian, Alibek Sailanbayev, Konstantin Mishchenko, Peter Richtárik

L-SVRG and L-Katyusha with Arbitrary Sampling

L-SVRG and L-Katyusha with Arbitrary Sampling

Xun Qian, Zheng Qu, Peter Richtárik

Journal of machine learning research 2019

On Stochastic Sign Descent Methods

On Stochastic Sign Descent Methods

Mher Safaryan, Peter Richtárik

A Stochastic Derivative Free Optimization Method with Momentum

A Stochastic Derivative Free Optimization Method with Momentum

Eduard A. Gorbunov, Adel Bibi, Ozan Sener, El Houcine Bergou, Peter Richtárik

International Conference on Learning Representations 2019

Stochastic Sign Descent Methods: New Algorithms and Better Theory

Stochastic Sign Descent Methods: New Algorithms and Better Theory

Mher Safaryan, Peter Richtárik

International Conference on Machine Learning 2019

Stochastic Proximal Langevin Algorithm: Potential Splitting and Nonasymptotic Rates

Stochastic Proximal Langevin Algorithm: Potential Splitting and Nonasymptotic Rates

A. Salim, D. Kovalev, Peter Richtárik

Neural Information Processing Systems 2019

Direct Nonlinear Acceleration

Direct Nonlinear Acceleration

Aritra Dutta, El Houcine Bergou, Yunming Xiao, Marco Canini, Peter Richtárik

EURO Journal on Computational Optimization 2019

One Method to Rule Them All: Variance Reduction for Data, Parameters and Many New Methods

One Method to Rule Them All: Variance Reduction for Data, Parameters and Many New Methods

Filip Hanzely, Peter Richtárik

arXiv.org 2019

A Stochastic Decoupling Method for Minimizing the Sum of Smooth and Non-Smooth Functions

A Stochastic Decoupling Method for Minimizing the Sum of Smooth and Non-Smooth Functions

Konstantin Mishchenko, Peter Richtárik

Revisiting Stochastic Extragradient

Revisiting Stochastic Extragradient

Konstantin Mishchenko, D. Kovalev, Egor Shulgin, Peter Richtárik, Yura Malitsky

International Conference on Artificial Intelligence and Statistics 2019

Natural Compression for Distributed Deep Learning

Natural Compression for Distributed Deep Learning

Samuel Horváth, Chen-Yu Ho, L. Horvath, Atal Narayan Sahu, Marco Canini, Peter Richtárik

Mathematical and Scientific Machine Learning 2019

A Unified Theory of SGD: Variance Reduction, Sampling, Quantization and Coordinate Descent

A Unified Theory of SGD: Variance Reduction, Sampling, Quantization and Coordinate Descent

Eduard A. Gorbunov, Filip Hanzely, Peter Richtárik

International Conference on Artificial Intelligence and Statistics 2019

RSN: Randomized Subspace Newton

RSN: Randomized Subspace Newton

Robert Mansel Gower, D. Kovalev, Felix Lieder, Peter Richtárik

Neural Information Processing Systems 2019

Best Pair Formulation & Accelerated Scheme for Non-Convex Principal Component Pursuit

Best Pair Formulation & Accelerated Scheme for Non-Convex Principal Component Pursuit

Aritra Dutta, Filip Hanzely, Jingwei Liang, Peter Richtárik

IEEE Transactions on Signal Processing 2019

Revisiting Randomized Gossip Algorithms: General Framework, Convergence Rates and Novel Block and Accelerated Protocols

Revisiting Randomized Gossip Algorithms: General Framework, Convergence Rates and Novel Block and Accelerated Protocols

Nicolas Loizou, Peter Richtárik

IEEE Transactions on Information Theory 2019

Stochastic Distributed Learning with Gradient Quantization and Variance Reduction

Stochastic Distributed Learning with Gradient Quantization and Variance Reduction

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

Convergence Analysis of Inexact Randomized Iterative Methods

Convergence Analysis of Inexact Randomized Iterative Methods

Nicolas Loizou, Peter Richtárik

SIAM Journal on Scientific Computing 2019

Scaling Distributed Machine Learning with In-Network Aggregation

Scaling Distributed Machine Learning with In-Network Aggregation

Amedeo Sapio, Marco Canini, Chen-Yu Ho, J. Nelson, Panos Kalnis, Changhoon Kim, A. Krishnamurthy, M. Moshref, Dan R. K. Ports, Peter Richtárik

Symposium on Networked Systems Design and Implementation 2019

Stochastic Three Points Method for Unconstrained Smooth Minimization

Stochastic Three Points Method for Unconstrained Smooth Minimization

El Houcine Bergou, Eduard A. Gorbunov, Peter Richtárik

SIAM Journal on Optimization 2019

A Stochastic Derivative-Free Optimization Method with Importance Sampling: Theory and Learning to Control

A Stochastic Derivative-Free Optimization Method with Importance Sampling: Theory and Learning to Control

Adel Bibi, El Houcine Bergou, Ozan Sener, Bernard Ghanem, Peter Richtárik

AAAI Conference on Artificial Intelligence 2019

Quasi-Newton methods for machine learning: forget the past, just sample

A. Berahas, Majid Jahani, Peter Richtárik, Martin Tak'avc

Optim. Methods Softw. 2019

99% of Distributed Optimization is a Waste of Time: The Issue and How to Fix it

99% of Distributed Optimization is a Waste of Time: The Issue and How to Fix it

Konstantin Mishchenko, Filip Hanzely, Peter Richtárik

99% of Parallel Optimization is Inevitably a Waste of Time

99% of Parallel Optimization is Inevitably a Waste of Time

Konstantin Mishchenko, Filip Hanzely, Peter Richtárik

arXiv.org 2019

SGD: General Analysis and Improved Rates

SGD: General Analysis and Improved Rates

Robert Mansel Gower, Nicolas Loizou, Xun Qian, Alibek Sailanbayev, Egor Shulgin, Peter Richtárik

International Conference on Machine Learning 2019

A Privacy Preserving Randomized Gossip Algorithm via Controlled Noise Insertion

A Privacy Preserving Randomized Gossip Algorithm via Controlled Noise Insertion

Filip Hanzely, Jakub Konecný, Nicolas Loizou, Peter Richtárik, Dmitry Grishchenko

arXiv.org 2019

Distributed Learning with Compressed Gradient Differences

Distributed Learning with Compressed Gradient Differences

Konstantin Mishchenko, Eduard A. Gorbunov, Martin Takác, Peter Richtárik

Optimization Methods and Software 2019

Don't Jump Through Hoops and Remove Those Loops: SVRG and Katyusha are Better Without the Outer Loop

Don't Jump Through Hoops and Remove Those Loops: SVRG and Katyusha are Better Without the Outer Loop

D. Kovalev, Samuel Horváth, Peter Richtárik

International Conference on Algorithmic Learning Theory 2019

SAGA with Arbitrary Sampling

SAGA with Arbitrary Sampling

Xun Qian, Zheng Qu, Peter Richtárik

International Conference on Machine Learning 2019

Randomized Projection Methods for Convex Feasibility: Conditioning and Convergence Rates

I. Necoara, Peter Richtárik, A. Pătraşcu

SIAM Journal on Optimization 2019

New Convergence Aspects of Stochastic Gradient Algorithms

New Convergence Aspects of Stochastic Gradient Algorithms

Lam M. Nguyen, Phuong Ha Nguyen, Peter Richtárik, K. Scheinberg, Martin Takác, Marten van Dijk

Journal of machine learning research 2018

A Stochastic Penalty Model for Convex and Nonconvex Optimization with Big Constraints

A Stochastic Penalty Model for Convex and Nonconvex Optimization with Big Constraints

Konstantin Mishchenko, Peter Richtárik

Provably Accelerated Randomized Gossip Algorithms

Provably Accelerated Randomized Gossip Algorithms

Nicolas Loizou, M. Rabbat, Peter Richtárik

IEEE International Conference on Acoustics, Speech, and Signal Processing 2018

Accelerated Coordinate Descent with Arbitrary Sampling and Best Rates for Minibatches

Filip Hanzely, Peter Richtárik

International Conference on Artificial Intelligence and Statistics 2018

Accelerated Gossip via Stochastic Heavy Ball Method

Accelerated Gossip via Stochastic Heavy Ball Method

Nicolas Loizou, Peter Richtárik

Allerton Conference on Communication, Control, and Computing 2018

Nonconvex Variance Reduced Optimization with Arbitrary Sampling

Nonconvex Variance Reduced Optimization with Arbitrary Sampling

Samuel Horváth, Peter Richtárik

International Conference on Machine Learning 2018

Matrix Completion Under Interval Uncertainty: Highlights

Jakub Marecek, Peter Richtárik, Martin Takác

ECML/PKDD 2018

SEGA: Variance Reduction via Gradient Sketching

SEGA: Variance Reduction via Gradient Sketching

Filip Hanzely, Konstantin Mishchenko, Peter Richtárik

Neural Information Processing Systems 2018

Accelerated Bregman proximal gradient methods for relatively smooth convex optimization

Filip Hanzely, Peter Richtárik, Lin Xiao

Computational optimization and applications 2018

Improving SAGA via a Probabilistic Interpolation with Gradient Descent

Improving SAGA via a Probabilistic Interpolation with Gradient Descent

Adel Bibi, Alibek Sailanbayev, Bernard Ghanem, Robert Mansel Gower, Peter Richtárik

A Nonconvex Projection Method for Robust PCA

A Nonconvex Projection Method for Robust PCA

Aritra Dutta, Filip Hanzely, Peter Richtárik

AAAI Conference on Artificial Intelligence 2018

Stochastic quasi-gradient methods: variance reduction via Jacobian sketching

R. Gower, Peter Richtárik, F. Bach

Mathematical programming 2018

Weighted Low-Rank Approximation of Matrices and Background Modeling

Weighted Low-Rank Approximation of Matrices and Background Modeling

Aritra Dutta, Xin Li, Peter Richtárik

arXiv.org 2018

Coordinate Descent Faceoff: Primal or Dual?

Coordinate Descent Faceoff: Primal or Dual?

Dominik Csiba, Peter Richtárik

International Conference on Algorithmic Learning Theory 2018

Fastest rates for stochastic mirror descent methods

Filip Hanzely, Peter Richtárik

Computational optimization and applications 2018

Randomized Block Cubic Newton Method

Randomized Block Cubic Newton Method

N. Doikov, Peter Richtárik

International Conference on Machine Learning 2018

Accelerated Stochastic Matrix Inversion: General Theory and Speeding up BFGS Rules for Faster Second-Order Optimization

Accelerated Stochastic Matrix Inversion: General Theory and Speeding up BFGS Rules for Faster Second-Order Optimization

R. Gower, Filip Hanzely, Peter Richtárik, Sebastian U. Stich

Neural Information Processing Systems 2018

Stochastic Spectral and Conjugate Descent Methods

Stochastic Spectral and Conjugate Descent Methods

D. Kovalev, Peter Richtárik, Eduard A. Gorbunov, Elnur Gasanov

Neural Information Processing Systems 2018

SGD and Hogwild! Convergence Without the Bounded Gradients Assumption

SGD and Hogwild! Convergence Without the Bounded Gradients Assumption

Lam M. Nguyen, Phuong Ha Nguyen, Marten van Dijk, Peter Richtárik, K. Scheinberg, Martin Takác

International Conference on Machine Learning 2018

The complexity of primal-dual fixed point methods for ridge regression

The complexity of primal-dual fixed point methods for ridge regression

Ademir Alves Riberio, Peter Richtárik

Linear Algebra and its Applications 2018

A Randomized Exchange Algorithm for Computing Optimal Approximate Designs of Experiments

Radoslav Harman, Lenka Filová, Peter Richtárik

Journal of the American Statistical Association 2018

Randomized projection methods for convex feasibility problems: conditioning and convergence rates

I. Necoara, Peter Richtárik, A. Pătraşcu

Momentum and stochastic momentum for stochastic gradient, Newton, proximal point and subspace descent methods

Nicolas Loizou, Peter Richtárik

Computational optimization and applications 2017

Online and Batch Supervised Background Estimation Via L1 Regression

Online and Batch Supervised Background Estimation Via L1 Regression

Aritra Dutta, Peter Richtárik

IEEE Workshop/Winter Conference on Applications of Computer Vision 2017

Linearly convergent stochastic heavy ball method for minimizing generalization error

Linearly convergent stochastic heavy ball method for minimizing generalization error

Nicolas Loizou, Peter Richtárik

arXiv.org 2017

Global Convergence of Arbitrary-Block Gradient Methods for Generalized Polyak-{\L} ojasiewicz Functions

Global Convergence of Arbitrary-Block Gradient Methods for Generalized Polyak-{\L} ojasiewicz Functions

Dominik Csiba, Peter Richtárik

Faster PET reconstruction with a stochastic primal-dual hybrid gradient method

Matthias Joachim Ehrhardt, P. Markiewicz, A. Chambolle, Peter Richtárik, J. Schott, C. Schönlieb

Optical Engineering + Applications 2017

A Batch-Incremental Video Background Estimation Model Using Weighted Low-Rank Approximation of Matrices

A Batch-Incremental Video Background Estimation Model Using Weighted Low-Rank Approximation of Matrices

Xin Li, Aritra Dutta, Peter Richtárik

2017 IEEE International Conference on Computer Vision Workshops (ICCVW) 2017

Privacy preserving randomized gossip algorithms

Privacy preserving randomized gossip algorithms

Filip Hanzely, Jakub Konevcn'y, Nicolas Loizou, Peter Richtárik, Dmitry Grishchenko

Stochastic Reformulations of Linear Systems: Algorithms and Convergence Theory

Stochastic Reformulations of Linear Systems: Algorithms and Convergence Theory

Peter Richtárik, Martin Takác

SIAM Journal on Matrix Analysis and Applications 2017

Parallel Stochastic Newton Method

Mojm'ir Mutn'y, Peter Richtárik

Journal of Computational Mathematics 2017

Extending the Reach of Big Data Optimization: Randomized Algorithms for Minimizing Relatively Smooth Functions

Filip Hanzely, Peter Richtárik

Linearly Convergent Randomized Iterative Methods for Computing the Pseudoinverse

Linearly Convergent Randomized Iterative Methods for Computing the Pseudoinverse

R. Gower, Peter Richtárik

Randomized Distributed Mean Estimation: Accuracy vs. Communication

Randomized Distributed Mean Estimation: Accuracy vs. Communication

Jakub Konecný, Peter Richtárik

Frontiers in Applied Mathematics and Statistics 2016

Optimization in High Dimensions via Accelerated, Parallel, and Proximal Coordinate Descent

Optimization in High Dimensions via Accelerated, Parallel, and Proximal Coordinate Descent

Olivier Fercoq, Peter Richtárik

SIAM Review 2016

Federated Learning: Strategies for Improving Communication Efficiency

Federated Learning: Strategies for Improving Communication Efficiency

Jakub Konecný, H. B. McMahan, Felix X. Yu, Peter Richtárik, A. Suresh, D. Bacon

arXiv.org 2016

A new perspective on randomized gossip algorithms

A new perspective on randomized gossip algorithms

Nicolas Loizou, Peter Richtárik

IEEE Global Conference on Signal and Information Processing 2016

Federated Optimization: Distributed Machine Learning for On-Device Intelligence

Federated Optimization: Distributed Machine Learning for On-Device Intelligence

Jakub Konecný, H. B. McMahan, Daniel Ramage, Peter Richtárik

arXiv.org 2016

AIDE: Fast and Communication Efficient Distributed Optimization

AIDE: Fast and Communication Efficient Distributed Optimization

Sashank J. Reddi, Jakub Konecný, Peter Richtárik, B. Póczos, Alex Smola

arXiv.org 2016

Coordinate Descent Face-Off: Primal or Dual?

Coordinate Descent Face-Off: Primal or Dual?

Dominik Csiba, Peter Richtárik

Stochastic Block BFGS: Squeezing More Curvature out of Data

Stochastic Block BFGS: Squeezing More Curvature out of Data

R. Gower, D. Goldfarb, Peter Richtárik

International Conference on Machine Learning 2016

Importance Sampling for Minibatches

Importance Sampling for Minibatches

Dominik Csiba, Peter Richtárik

Journal of machine learning research 2016

Randomized Quasi-Newton Updates Are Linearly Convergent Matrix Inversion Algorithms

Randomized Quasi-Newton Updates Are Linearly Convergent Matrix Inversion Algorithms

R. Gower, Peter Richtárik

SIAM Journal on Matrix Analysis and Applications 2016

Even Faster Accelerated Coordinate Descent Using Non-Uniform Sampling

Even Faster Accelerated Coordinate Descent Using Non-Uniform Sampling

Zeyuan Allen-Zhu, Zheng Qu, Peter Richtárik, Yang Yuan

International Conference on Machine Learning 2015

Stochastic Dual Ascent for Solving Linear Systems

Stochastic Dual Ascent for Solving Linear Systems

Robert Mansel Gower, Peter Richtárik

arXiv.org 2015

Distributed optimization with arbitrary local solvers

Chenxin Ma, Jakub Konecný, Martin Jaggi, Virginia Smith, Michael I. Jordan, Peter Richtárik, Martin Takác

Optim. Methods Softw. 2015

Quartz: Randomized Dual Coordinate Ascent with Arbitrary Sampling

Quartz: Randomized Dual Coordinate Ascent with Arbitrary Sampling

Zheng Qu, Peter Richtárik, Tong Zhang

Neural Information Processing Systems 2015

Distributed Mini-Batch SDCA

Distributed Mini-Batch SDCA

Martin Takác, Peter Richtárik, N. Srebro

arXiv.org 2015

Randomized Iterative Methods for Linear Systems

Randomized Iterative Methods for Linear Systems

Robert Mansel Gower, Peter Richtárik

SIAM Journal on Matrix Analysis and Applications 2015

Primal Method for ERM with Flexible Mini-batching Schemes and Non-convex Losses

Primal Method for ERM with Flexible Mini-batching Schemes and Non-convex Losses

Dominik Csiba, Peter Richtárik

arXiv.org 2015

Mini-Batch Semi-Stochastic Gradient Descent in the Proximal Setting

Mini-Batch Semi-Stochastic Gradient Descent in the Proximal Setting

Jakub Konecný, Jie Liu, Peter Richtárik, Martin Takác

IEEE Journal on Selected Topics in Signal Processing 2015

Stochastic Dual Coordinate Ascent with Adaptive Probabilities

Stochastic Dual Coordinate Ascent with Adaptive Probabilities

Dominik Csiba, Zheng Qu, Peter Richtárik

International Conference on Machine Learning 2015

Adding vs. Averaging in Distributed Primal-Dual Optimization

Adding vs. Averaging in Distributed Primal-Dual Optimization

Chenxin Ma, Virginia Smith, Martin Jaggi, Michael I. Jordan, Peter Richtárik, Martin Takác

International Conference on Machine Learning 2015

SDNA: Stochastic Dual Newton Ascent for Empirical Risk Minimization

SDNA: Stochastic Dual Newton Ascent for Empirical Risk Minimization

Zheng Qu, Peter Richtárik, Martin Takác, Olivier Fercoq

International Conference on Machine Learning 2015

Coordinate descent with arbitrary sampling I: algorithms and complexity†

Zheng Qu, Peter Richtárik

Optim. Methods Softw. 2014

Coordinate descent with arbitrary sampling II: expected separable overapproximation

Zheng Qu, Peter Richtárik

Optim. Methods Softw. 2014

Semi-stochastic coordinate descent

Jakub Konecný, Zheng Qu, Peter Richtárik

Optim. Methods Softw. 2014

Randomized Dual Coordinate Ascent with Arbitrary Sampling

Randomized Dual Coordinate Ascent with Arbitrary Sampling

Zheng Qu, Peter Richtárik, Tong Zhang

arXiv.org 2014

S2CD: Semi-stochastic coordinate descent

Jakub Konecný, Zheng Qu, Peter Richtárik

Simple Complexity Analysis of Direct Search

Jakub Konecný, Peter Richtárik

arXiv.org 2014

Simple Complexity Analysis of Simplified Direct Search

Simple Complexity Analysis of Simplified Direct Search

Jakub Konevcn'y, Peter Richtárik

Matrix completion under interval uncertainty

Matrix completion under interval uncertainty

Jakub Marecek, Peter Richtárik, Martin Takác

European Journal of Operational Research 2014

Distributed Block Coordinate Descent for Minimizing Partially Separable Functions

Jakub Marecek, Peter Richtárik, Martin Takác

Fast distributed coordinate descent for non-strongly convex losses

Olivier Fercoq, Zheng Qu, Peter Richtárik, Martin Takác

International Workshop on Machine Learning for Signal Processing 2014

Accelerated, Parallel, and Proximal Coordinate Descent

Accelerated, Parallel, and Proximal Coordinate Descent

Olivier Fercoq, Peter Richtárik

SIAM Journal on Optimization 2013

Semi-Stochastic Gradient Descent Methods

Semi-Stochastic Gradient Descent Methods

Jakub Konecný, Peter Richtárik

Frontiers in Applied Mathematics and Statistics 2013

TOP-SPIN: TOPic discovery via Sparse Principal component INterference

M. Takác, S. Ahipaşaoğlu, Ngai-Man Cheung, Peter Richtárik

Modeling and Optimization: Theory and Applications 2013

On optimal probabilities in stochastic coordinate descent methods

Peter Richtárik, Martin Takác

Optimization Letters 2013

Distributed Coordinate Descent Method for Learning with Big Data

Distributed Coordinate Descent Method for Learning with Big Data

Peter Richtárik, Martin Takác

Journal of machine learning research 2013

Smooth minimization of nonsmooth functions with parallel coordinate descent methods

Olivier Fercoq, Peter Richtárik

Modeling and Optimization: Theory and Applications 2013

Separable approximations and decomposition methods for the augmented Lagrangian

R. Tappenden, Peter Richtárik, Burak Büke

Optim. Methods Softw. 2013

Inexact Coordinate Descent: Complexity and Preconditioning

R. Tappenden, Peter Richtárik, J. Gondzio

Journal of Optimization Theory and Applications 2013

Mini-Batch Primal and Dual Methods for SVMs

Mini-Batch Primal and Dual Methods for SVMs

Martin Takác, A. Bijral, Peter Richtárik, N. Srebro

International Conference on Machine Learning 2013

Alternating maximization: unifying framework for 8 sparse PCA formulations and efficient parallel codes

Peter Richtárik, Martin Takác, S. Ahipaşaoğlu

Optimization and Engineering 2012

Optimal diagnostic tests for sporadic Creutzfeldt-Jakob disease based on support vector machine classification of RT-QuIC data

Optimal diagnostic tests for sporadic Creutzfeldt-Jakob disease based on support vector machine classification of RT-QuIC data

W. Hulme, Peter Richtárik, L. McGuire, A. Green

arXiv.org 2012

Parallel coordinate descent methods for big data optimization

Peter Richtárik, Martin Takác

Mathematical programming 2012

Approximate Level Method for Nonsmooth Convex Minimization

Peter Richtárik

Journal of Optimization Theory and Applications 2011

Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function

Peter Richtárik, Martin Takác

Mathematical programming 2011

Improved Algorithms for Convex Minimization in Relative Scale

Peter Richtárik

SIAM Journal on Optimization 2011

Approximate level method

Approximate level method

Peter Richtárik

Generalized Power Method for Sparse Principal Component Analysis

Generalized Power Method for Sparse Principal Component Analysis

M. Journée, Y. Nesterov, Peter Richtárik, R. Sepulchre

Journal of machine learning research 2008

Federated Sampling with Langevin Algorithm under Isoperimetry

Federated Sampling with Langevin Algorithm under Isoperimetry

Lukang Sun, Adil Salim, Peter Richtárik

Trans. Mach. Learn. Res. 2024

DASHA: Distributed Nonconvex Optimization with Communication Compression and Optimal Oracle Complexity

A. Tyurin, Peter Richtárik

International Conference on Learning Representations 2023

A Damped Newton Method Achieves Global $\mathcal O \left(\frac{1}{k^2}\right)$ and Local Quadratic Convergence Rate

Slavomír Hanzely, Dmitry Kamzolov, D. Pasechnyuk, A. Gasnikov, Peter Richtárik, Martin Takác

Neural Information Processing Systems 2022

Smoothness-Aware Quantization Techniques

Smoothness-Aware Quantization Techniques

Bokun Wang, Mher Safaryan, Peter Richtárik

arXiv.org 2021

On Server-Side Stepsizes in Federated Optimization: Theory Explaining the Heuristics

Grigory Malinovsky, Konstantin Mishchenko, Peter Richtárik

Complexity Analysis of Stein Variational Gradient Descent Under Talagrand's Inequality T1

Complexity Analysis of Stein Variational Gradient Descent Under Talagrand's Inequality T1

A. Salim, Lukang Sun, Peter Richtárik

arXiv.org 2021

IntSGD: Floatless Compression of Stochastic Gradients

IntSGD: Floatless Compression of Stochastic Gradients

Konstantin Mishchenko, Bokun Wang, D. Kovalev, Peter Richtárik

arXiv.org 2021

Error Compensated Loopless SVRG for Distributed Optimization

Error Compensated Loopless SVRG for Distributed Optimization

Xun Qian, Hanze Dong, Peter Richtárik, Tong Zhang

Error Compensated Proximal SGD and RDA

Error Compensated Proximal SGD and RDA

Xun Qian, Hanze Dong, Peter Richtárik, Tong Zhang

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

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

Konstantin Mishchenko, Filip Hanzely, Peter Richtárik

Conference on Uncertainty in Artificial Intelligence 2020

Programme on “ Modern Maximal Monotone Operator Theory : From Nonsmooth Optimization to Differential Inclusions ” January 28 – March 8 , 2019 organized

Heinz H. Bauschke, C. Kanzow, Peter Richtárik, Mathias Staudigl, V. Cevher, O. Scherzer, S. Matsushita, I. Yamada

IntML: Natural Compression for Distributed Deep Learning

IntML: Natural Compression for Distributed Deep Learning

Samuel Horváth, Chen-Yu Ho, L. Horvath, Atal Narayan Sahu, Marco Canini, Peter Richtárik

SGD with Arbitrary Sampling: General Analysis and Improved Rates

Xun Qian, Peter Richtárik, R. Gower, Alibek Sailanbayev, Nicolas Loizou, Egor Shulgin

International Conference on Machine Learning 2019

Ju n 20 15 Coordinate Descent with Arbitrary Sampling I : Algorithms and Complexity ∗

Ju n 20 15 Coordinate Descent with Arbitrary Sampling I : Algorithms and Complexity ∗

Zheng Qu, Peter Richtárik

Explorer Coordinate Descent with Arbitrary Sampling I : Algorithms and Complexity

Explorer Coordinate Descent with Arbitrary Sampling I : Algorithms and Complexity

Zheng Qu, Peter Richtárik

Edinburgh Research Explorer Matrix Completion under Interval Uncertainty

Edinburgh Research Explorer Matrix Completion under Interval Uncertainty

Jakub Marecek, Peter Richtárik, M. Takác

Title Coordinate descent with arbitrary sampling I : algorithms andcomplexity

Title Coordinate descent with arbitrary sampling I : algorithms andcomplexity

Zheng Qu, Peter Richtárik

On Optimal Solutions to Planetesimal Growth Models

On Optimal Solutions to Planetesimal Growth Models

D. Forgan, Peter Richtárik

Explorer Coordinate Descent with Arbitrary Sampling I : Algorithms and Complexity

Peter Richtárik

Explorer Accelerated , Parallel and Proximal Coordinate Descent

Explorer Accelerated , Parallel and Proximal Coordinate Descent

Peter Richtárik

Edinburgh Research Explorer Alternating Maximization

Edinburgh Research Explorer Alternating Maximization

Peter Richtárik, Martin Takác, S. Ahipaşaoğlu

Finding sparse approximations to extreme eigenvectors: generalized power method for sparse PCA and extensions

Peter Richtárik

Efficiency of randomized coordinate descent methods on minimization problems with a composite objective function

Peter Richtárik

Efficient Serial and Parallel Coordinate Descent Methods for Huge-Scale Truss Topology Design

Peter Richtárik, Martin Takác

OR 2011

Simultaneously solving seven optimization problems in relative scale

Simultaneously solving seven optimization problems in relative scale

Peter Richtárik

2008 / 83 Approximate level method

2008 / 83 Approximate level method

Peter Richtárik

Some algorithms for large-scale linear and convex minimization in relative scale

Some algorithms for large-scale linear and convex minimization in relative scale

M. Todd, Peter Richtárik

SOME ALGORITHMS FOR LARGE-SCALE LINEAR

Peter Richtárik