Michał Dereziński

422 total citations
18 papers, 43 citations indexed

About

Michał Dereziński is a scholar working on Artificial Intelligence, Statistics and Probability and Computational Mechanics. According to data from OpenAlex, Michał Dereziński has authored 18 papers receiving a total of 43 indexed citations (citations by other indexed papers that have themselves been cited), including 14 papers in Artificial Intelligence, 6 papers in Statistics and Probability and 5 papers in Computational Mechanics. Recurrent topics in Michał Dereziński's work include Stochastic Gradient Optimization Techniques (7 papers), Machine Learning and Algorithms (6 papers) and Sparse and Compressive Sensing Techniques (5 papers). Michał Dereziński is often cited by papers focused on Stochastic Gradient Optimization Techniques (7 papers), Machine Learning and Algorithms (6 papers) and Sparse and Compressive Sensing Techniques (5 papers). Michał Dereziński collaborates with scholars based in United States, Italy and Israel. Michał Dereziński's co-authors include Manfred K. Warmuth, Daniel Hsu, Michael W. Mahoney, Rajiv Khanna, Dhruv Mahajan, Kenneth L. Clarkson, Younghyun Cho, S. Sathiya Keerthi, J. Demmel and Mark Rudelson and has published in prestigious journals such as Mathematical Programming, SIAM Journal on Matrix Analysis and Applications and HAL (Le Centre pour la Communication Scientifique Directe).

In The Last Decade

Michał Dereziński

16 papers receiving 42 citations

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name	h						Papers	Cites
Michał Dereziński United States	4	24	12	10	10	8	18	43
Aymeric Dieuleveut France	4	38 1.6×	17 1.4×	6 0.6×	17 1.7×	9 1.1×	12	56
Rahul Kidambi United States	5	31 1.3×	13 1.1×	8 0.8×	4 0.4×	4 0.5×	12	40
Gauthier Gidel Canada	5	28 1.2×	16 1.3×	6 0.6×	5 0.5×	4 0.5×	12	36
Theodor Misiakiewicz United States	5	37 1.5×	16 1.3×	14 1.4×	15 1.5×	4 0.5×	7	60
Filip Hanzely Saudi Arabia	5	27 1.1×	16 1.3×	4 0.4×	2 0.2×	10 1.3×	8	63
S. Sandilya United States	3	20 0.8×	7 0.6×	19 1.9×	8 0.8×	1 0.1×	9	51
Behrooz Ghorbani United States	4	47 2.0×	6 0.5×	18 1.8×	9 0.9×	3 0.4×	6	57
Wenlin Chen United States	2	26 1.1×	3 0.3×	8 0.8×	5 0.5×	5 0.6×	3	50
Eduard Gorbunov Russia	6	42 1.8×	35 2.9×	2 0.2×	5 0.5×	18 2.3×	14	70
Pierre Dusart France	5	33 1.4×	6 0.5×	6 0.6×	1 0.1×	19 2.4×	10	147

Countries citing papers authored by Michał Dereziński

Since Specialization

Citations

This map shows the geographic impact of Michał Dereziński'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 Michał Dereziński with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Michał Dereziński more than expected).

Fields of papers citing papers by Michał Dereziński

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Michał Dereziński. 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 Michał Dereziński. The network helps show where Michał Dereziński may publish in the future.

Co-authorship network of co-authors of Michał Dereziński

This figure shows the co-authorship network connecting the top 25 collaborators of Michał Dereziński. A scholar is included among the top collaborators of Michał Dereziński 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 Michał Dereziński. Michał Dereziński is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

Sort: Min cites: Since: Top N: Style:

18 of 18 papers shown

Dereziński, Michał, et al.. (2025). Randomized Kaczmarz Methods with Beyond-Krylov Convergence. SIAM Journal on Matrix Analysis and Applications. 46(4). 2558–2588.

Cho, Younghyun, et al.. (2025). Surrogate-Based Autotuning for Randomized Sketching Algorithms in Regression Problems. SIAM Journal on Matrix Analysis and Applications. 46(2). 1247–1279.

Dereziński, Michał, et al.. (2024). Optimal Embedding Dimension for Sparse Subspace Embeddings. 1106–1117. 1 indexed citations

Dereziński, Michał & Michael W. Mahoney. (2024). Recent and Upcoming Developments in Randomized Numerical Linear Algebra for Machine Learning. 6470–6479. 1 indexed citations

Dereziński, Michał, et al.. (2024). Sharp Analysis of Sketch-and-Project Methods via a Connection to Randomized Singular Value Decomposition. SIAM Journal on Mathematics of Data Science. 6(1). 127–153. 8 indexed citations

Dereziński, Michał, et al.. (2022). Hessian averaging in stochastic Newton methods achieves superlinear convergence. Mathematical Programming. 201(1-2). 473–520. 3 indexed citations

Dereziński, Michał, Rajiv Khanna, & Michael W. Mahoney. (2021). Improved Guarantees and a Multiple-descent Curve for Column Subset Selection and the Nystrom Method (Extended Abstract). 4765–4769. 1 indexed citations

Dereziński, Michał, et al.. (2020). Exact expressions for double descent and implicit regularization via surrogate random design. Neural Information Processing Systems. 33. 5152–5164. 2 indexed citations

Dereziński, Michał, Rajiv Khanna, & Michael W. Mahoney. (2020). Improved guarantees and a multiple-descent curve for Column Subset Selection and the Nyström method. arXiv (Cornell University). 33. 4953–4964. 2 indexed citations

10.

Dereziński, Michał, et al.. (2019). Exact sampling of determinantal point processes with sublinear time preprocessing. HAL (Le Centre pour la Communication Scientifique Directe). 2 indexed citations

11.

Dereziński, Michał, Manfred K. Warmuth, & Daniel Hsu. (2019). Correcting the bias in least squares regression with volume-rescaled sampling. International Conference on Artificial Intelligence and Statistics. 944–953. 2 indexed citations

12.

Dereziński, Michał, Kenneth L. Clarkson, Michael W. Mahoney, & Manfred K. Warmuth. (2019). Minimax experimental design: Bridging the gap between statistical and worst-case approaches to least squares regression.. Conference on Learning Theory. 1050–1069. 1 indexed citations

13.

Dereziński, Michał, Manfred K. Warmuth, & Daniel Hsu. (2018). Leveraged volume sampling for linear regression. arXiv (Cornell University). 31. 2505–2514. 12 indexed citations

14.

Dereziński, Michał, Dhruv Mahajan, S. Sathiya Keerthi, S. V. N. Vishwanathan, & Markus Weimer. (2017). Batch-Expansion Training: An Efficient Optimization Paradigm for Machine Learning.. arXiv (Cornell University). 1 indexed citations

15.

Dereziński, Michał & Manfred K. Warmuth. (2017). Subsampling for Ridge Regression via Regularized Volume Sampling. arXiv (Cornell University). 716–725. 2 indexed citations

16.

Dereziński, Michał & Manfred K. Warmuth. (2017). Unbiased estimates for linear regression via volume sampling. Neural Information Processing Systems. 30. 3084–3093. 3 indexed citations

17.

Dereziński, Michał, Dhruv Mahajan, S. Sathiya Keerthi, S. V. N. Vishwanathan, & Markus Weimer. (2017). Batch-Expansion Training: An Efficient Optimization Framework. arXiv (Cornell University). 736–744. 1 indexed citations

18.

Dereziński, Michał & Manfred K. Warmuth. (2014). The limits of squared Euclidean distance regularization. Neural Information Processing Systems. 27. 2807–2815. 1 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.

Explore authors with similar magnitude of impact