2026 Peter Richtárik: Computer Science Researcher – H-Index, Publications & Awards

Discipline name	D-Index	World Ranking	Current World Ranking	National Ranking	Current National Ranking	Publications	Citations
Computer Science	59	3383	3287	15	15	210	16666

Overview

Peter Richtárik is affiliated with the King Abdullah University of Science and Technology in Saudi Arabia. Their research spans multiple domains primarily within computer science and engineering, with a significant number of publications focusing on artificial intelligence and computational mechanics.

Their scholarly contributions cover a wide array of subfields, including:

Artificial Intelligence
Computational Mechanics
Computer Networks and Communications
Computational Theory and Mathematics
Statistics and Probability

Richtárik's work addresses key topics related to optimization and machine learning technologies, often focusing on stochastic methods and privacy concerns. The main topics of their research include:

Stochastic Gradient Optimization Techniques
Sparse and Compressive Sensing Techniques
Privacy-Preserving Technologies in Data
Advanced Optimization Algorithms Research
Advanced Bandit Algorithms Research
Machine Learning and Extreme Learning Machines (ELM)
Machine Learning and Algorithms

Their frequent publication venues reflect a diverse engagement with both open-access repositories and established journals. These venues include:

arXiv (Cornell University)
King Abdullah University of Science and Technology Repository
Computational Optimization and Applications
Optimization Methods & Software
Journal of Optimization Theory and Applications

Some recent papers authored or co-authored by Peter Richtárik include:

"Federated Learning of a Mixture of Global and Local Models," 2020, arXiv (Cornell University)
"A Field Guide to Federated Optimization," 2021, arXiv (Cornell University)
"Optimal Client Sampling for Federated Learning," 2020, arXiv (Cornell University)
"Momentum and stochastic momentum for stochastic gradient, Newton, proximal point and subspace descent methods," 2020, Computational Optimization and Applications
"Lower Bounds and Optimal Algorithms for Personalized Federated Learning," 2020, arXiv (Cornell University)

Collaboration plays a notable role in their research output, with frequent co-authors including:

Samuel Horváth
Grigory Malinovsky
Dmitry Kovalev
Laurent Condat
Eduard Gorbunov

Best Publications

Federated Learning: Strategies for Improving Communication Efficiency

Jakub Konečný;H. Brendan McMahan;Felix X. Yu;Peter Richtarik

3802
Citations
Federated Optimization: Distributed Machine Learning for On-Device Intelligence

Jakub Konečný;H. Brendan McMahan;Daniel Ramage;Peter Richtarik

1915
Citations
Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function

Peter Richtárik;Martin Takáč

811
Citations
Generalized Power Method for Sparse Principal Component Analysis

Michel Journée;Yurii Nesterov;Peter Richtárik;Rodolphe Sepulchre

665
Citations
Parallel coordinate descent methods for big data optimization

Peter Richtárik;Martin Takáč

515
Citations
Accelerated, Parallel, and Proximal Coordinate Descent

Olivier Fercoq;Peter Richtárik

390
Citations
Mini-Batch Semi-Stochastic Gradient Descent in the Proximal Setting

Jakub Konecny;Jie Liu;Peter Richtarik;Martin Takac

327
Citations
Federated Learning of a Mixture of Global and Local Models

Filip Hanzely;Peter Richtarik

275
Citations
Distributed coordinate descent method for learning with big data

Peter Richtárik;Martin Takáč

230
Citations
Semi-Stochastic Gradient Descent Methods

Jakub Konečný;Peter Richtárik

214
Citations
Distributed optimization with arbitrary local solvers

Chenxin Ma;Jakub Konečný;Martin Jaggi;Virginia Smith

205
Citations
Scaling Distributed Machine Learning with In-Network Aggregation

Amedeo Sapio;Marco Canini;Chen-Yu Ho;Jacob Nelson

189
Citations
Mini-Batch Primal and Dual Methods for SVMs

Martin Takac;Avleen Bijral;Peter Richtarik;Nati Srebro

185
Citations
Momentum and stochastic momentum for stochastic gradient, Newton, proximal point and subspace descent methods

Nicolas Loizou;Peter Richtárik

185
Citations
Stochastic Primal-Dual Hybrid Gradient Algorithm with Arbitrary Sampling and Imaging Applications

Antonin Chambolle;Matthias J. Ehrhardt;Peter Richtárik;Peter Richtárik;Carola-Bibiane Schönlieb

180
Citations
Tighter Theory for Local SGD on Identical and Heterogeneous Data

Ahmed Khaled;Konstantin Mishchenko;Peter Richtarik

172
Citations
A Field Guide to Federated Optimization

Jianyu Wang;Zachary Charles;Zheng Xu;Gauri Joshi

171
Citations
Even faster accelerated coordinate descent using non-uniform sampling

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

166
Citations
Adding vs. Averaging in Distributed Primal-Dual Optimization

Chenxin Ma;Virginia Smith;Martin Jaggi;Michael Jordan

165
Citations
SGD: General Analysis and Improved Rates

Robert Mansel Gower;Nicolas Loizou;Xun Qian;Alibek Sailanbayev

159
Citations
Distributed Learning with Compressed Gradient Differences.

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

152
Citations
First Analysis of Local GD on Heterogeneous Data

Ahmed Khaled;Konstantin Mishchenko;Peter Richtárik

104
Citations
Optimal Client Sampling for Federated Learning

Wenlin Chen;Samuel Horvath;Peter Richtarik

85
Citations
On Biased Compression for Distributed Learning.

Aleksandr Beznosikov;Samuel Horváth;Peter Richtárik;Mher Safaryan

75
Citations
Better Theory for SGD in the Nonconvex World

Ahmed Khaled;Peter Richtárik

59
Citations

Frequent Co-Authors

Michael I. Jordan University of California, Berkeley

Yurii Nesterov Université Catholique de Louvain

Bernard Ghanem King Abdullah University of Science and Technology

Marco Canini King Abdullah University of Science and Technology

Francis Bach École Normale Supérieure

Marten van Dijk University of Connecticut

Katya Scheinberg Cornell University

Ngai-Man Cheung Singapore University of Technology and Design

Tong Zhang University of Illinois at Urbana-Champaign

Rodolphe Sepulchre University of Cambridge

External Links

Personal website of Peter Richtárik Google Scholar page

If you think any of the details on this page are incorrect, let us know.

Related Online Degrees & Career Pathways

Exploring Computer Science in the USA opens doors to a range of online degree programs and career options beyond traditional pathways. For students concerned about their academic record, there are several college with low gpa options, making higher education increasingly accessible.

The flexibility of an online computer science degree means learners can fast-track their studies and enter tech careers sooner. Accelerated programs and distance learning can also help balance work and study commitments.

Computer Science is a gateway to related fields, such as engineering or environmental science. Curious about interdisciplinary opportunities? Discover online environmental engineering degree science and engineering for a blend of technology, sustainability, and innovation.

Graduates can explore diverse roles in government, tech, consulting, or research. Wondering about the broader prospects? Learn what can you get with an environmental science degree, and see how computing skills complement careers in data analysis, system design, and environmental solutions.