Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies
if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the
same subfield and year (this is the minimum needed to enter the top 1%, not the average
within it), or reaches the top citation threshold in at least one of its specific research
topics.
Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function
2012345 citationsPeter Richtárik, Martin Takáčprofile →
Peers — A (Enhanced Table)
Peers by citation overlap · career bar shows stage (early→late)
cites ·
hero ref
Countries citing papers authored by Peter Richtárik
Since
Specialization
Citations
This map shows the geographic impact of Peter Richtárik's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Peter Richtárik with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Peter Richtárik more than expected).
This network shows the impact of papers produced by Peter Richtárik. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Peter Richtárik. The network helps show where Peter Richtárik may publish in the future.
Co-authorship network of co-authors of Peter Richtárik
This figure shows the co-authorship network connecting the top 25 collaborators of Peter Richtárik.
A scholar is included among the top collaborators of Peter Richtárik based on the total number of
citations received by their joint publications. Widths of edges
represent the number of papers authors have co-authored together.
Node borders
signify the number of papers an author published with Peter Richtárik. Peter Richtárik is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
Li, Zhize, et al.. (2021). PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization. King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology). 6286–6295.4 indexed citations
4.
Richtárik, Peter, et al.. (2021). Distributed Second Order Methods with Fast Rates and Compressed Communication. King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology). 4617–4628.3 indexed citations
5.
Kovalev, Dmitry, et al.. (2020). From Local SGD to Local Fixed Point Methods for Federated Learning. International Conference on Machine Learning. 1. 6692–6701.24 indexed citations
6.
Hanzely, Filip, Dmitry Kovalev, & Peter Richtárik. (2020). Variance Reduced Coordinate Descent with Acceleration: New Method With a Surprising Application to Finite-Sum Problems. King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology). 1. 4039–4048.1 indexed citations
7.
Mishchenko, Konstantin, et al.. (2020). Revisiting Stochastic Extragradient. King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology). 4573–4582.3 indexed citations
8.
Mishchenko, Konstantin, Filip Hanzely, & Peter Richtárik. (2020). 99% of Worker-Master Communication in Distributed Optimization Is Not Needed.. King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology). 979–988.3 indexed citations
9.
Hanzely, Filip, et al.. (2020). Lower Bounds and Optimal Algorithms for Personalized Federated Learning. King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology). 33. 2304–2315.2 indexed citations
10.
Mishchenko, Konstantin, et al.. (2020). Random Reshuffling: Simple Analysis with Vast Improvements. King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology). 33. 17309–17320.2 indexed citations
11.
Mishchenko, Konstantin, et al.. (2019). Better Communication Complexity for Local SGD. King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology).4 indexed citations
12.
Richtárik, Peter, et al.. (2019). SGD with Arbitrary Sampling: General Analysis and Improved Rates.. International Conference on Machine Learning. 5200–5209.2 indexed citations
13.
Qu, Zheng, et al.. (2019). SAGA with Arbitrary Sampling. King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology). 5190–5199.3 indexed citations
14.
Horváth, Samuel & Peter Richtárik. (2019). Nonconvex Variance Reduced Optimization with Arbitrary Sampling. King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology). 2781–2789.6 indexed citations
15.
Richtárik, Peter, et al.. (2018). Randomized Block Cubic Newton Method. King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology). 1290–1298.2 indexed citations
16.
Nguyen, Lam M., Phuong Ha Nguyen, Marten van Dijk, et al.. (2018). SGD and Hogwild! Convergence Without the Bounded Gradients Assumption. King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology). 3750–3758.14 indexed citations
17.
Hanzely, Filip, Konstantin Mishchenko, & Peter Richtárik. (2018). SEGA: Variance Reduction via Gradient Sketching. King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology). 31. 2082–2093.4 indexed citations
18.
Allen-Zhu, Zeyuan, Zheng Qu, Peter Richtárik, & Yuan Yang. (2016). Even faster accelerated coordinate descent using non-uniform sampling. International Conference on Machine Learning. 1110–1119.20 indexed citations
19.
Konečný, Jakub & Peter Richtárik. (2014). Simple Complexity Analysis of Direct Search.. arXiv (Cornell University).4 indexed citations
20.
Takáč, Martin, et al.. (2013). Mini-Batch Primal and Dual Methods for SVMs. International Conference on Machine Learning. 1022–1030.31 indexed citations
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive
bibliographic database. While OpenAlex provides broad and valuable coverage of the global
research landscape, it—like all bibliographic datasets—has inherent limitations. These include
incomplete records, variations in author disambiguation, differences in journal indexing, and
delays in data updates. As a result, some metrics and network relationships displayed in
Rankless may not fully capture the entirety of a scholar's output or impact.