Matus Telgarsky

2.3k total citations · 1 hit paper
15 papers, 469 citations indexed

About

Matus Telgarsky is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition and Computational Mechanics. According to data from OpenAlex, Matus Telgarsky has authored 15 papers receiving a total of 469 indexed citations (citations by other indexed papers that have themselves been cited), including 13 papers in Artificial Intelligence, 3 papers in Computer Vision and Pattern Recognition and 3 papers in Computational Mechanics. Recurrent topics in Matus Telgarsky's work include Stochastic Gradient Optimization Techniques (6 papers), Sparse and Compressive Sensing Techniques (3 papers) and Machine Learning and Algorithms (3 papers). Matus Telgarsky is often cited by papers focused on Stochastic Gradient Optimization Techniques (6 papers), Sparse and Compressive Sensing Techniques (3 papers) and Machine Learning and Algorithms (3 papers). Matus Telgarsky collaborates with scholars based in United States, Netherlands and United Kingdom. Matus Telgarsky's co-authors include Animashree Anandkumar, Rong Ge, Daniel Hsu, Sham M. Kakade, Ziwei Ji, Andrea Vattani, Sanjoy Dasgupta, Robert E. Schapire, Sébastien Lahaie and Alina Beygelzimer and has published in prestigious journals such as Journal of Machine Learning Research, arXiv (Cornell University) and Neural Information Processing Systems.

In The Last Decade

Matus Telgarsky

14 papers receiving 440 citations

Hit Papers

align trajectories

What are hit papers?

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.

Tensor decompositions for learning latent variable models

2014 371 citations Animashree Anandkumar, Rong Ge et al. Journal of Machine Learning Research profile →

Peers — A (Enhanced Table)

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

Name	h						Papers	Cites
Matus Telgarsky United States	7	223	211	121	66	54	15	469
Kim Batselier Hong Kong	14	87 0.4×	212 1.0×	153 1.3×	59 0.9×	48 0.9×	51	457
Elias Tsigaridas France	14	90 0.4×	104 0.5×	178 1.5×	58 0.9×	50 0.9×	61	608
Berkant Savas Sweden	10	140 0.6×	282 1.3×	151 1.2×	71 1.1×	85 1.6×	19	531
Chunfeng Cui China	12	41 0.2×	158 0.7×	74 0.6×	21 0.3×	45 0.8×	39	394
Luis Rademacher United States	7	193 0.9×	44 0.2×	180 1.5×	66 1.0×	98 1.8×	26	401
Muthu Manikandan Baskaran United States	14	185 0.8×	165 0.8×	31 0.3×	16 0.2×	74 1.4×	41	831
Mariya Ishteva Belgium	9	52 0.2×	175 0.8×	98 0.8×	51 0.8×	41 0.8×	26	301
Shaden Smith United States	13	220 1.0×	353 1.7×	42 0.3×	27 0.4×	88 1.6×	19	564
Akshay Krishnamurthy United States	13	293 1.3×	24 0.1×	70 0.6×	40 0.6×	83 1.5×	40	457
Bora Uçar France	12	96 0.4×	40 0.2×	37 0.3×	23 0.3×	70 1.3×	35	543

Countries citing papers authored by Matus Telgarsky

Since Specialization

Citations

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

Fields of papers citing papers by Matus Telgarsky

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

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

Co-authorship network of co-authors of Matus Telgarsky

This figure shows the co-authorship network connecting the top 25 collaborators of Matus Telgarsky. A scholar is included among the top collaborators of Matus Telgarsky 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 Matus Telgarsky. Matus Telgarsky 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:

15 of 15 papers shown

1.

Ji, Ziwei & Matus Telgarsky. (2021). Characterizing the implicit bias via a primal-dual analysis.. 772–804. 1 indexed citations

2.

Ji, Ziwei & Matus Telgarsky. (2020). Polylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow ReLU networks. arXiv (Cornell University). 10 indexed citations

3.

Ji, Ziwei & Matus Telgarsky. (2020). Directional convergence and alignment in deep learning. Neural Information Processing Systems. 33. 17176–17186. 2 indexed citations

4.

Ji, Ziwei, et al.. (2020). Neural tangent kernels, transportation mappings, and universal approximation. arXiv (Cornell University). 2 indexed citations

5.

Ji, Ziwei, Miroslav Dudı́k, Robert E. Schapire, & Matus Telgarsky. (2020). Gradient descent follows the regularization path for general losses.. Conference on Learning Theory. 2109–2136.

6.

Ji, Ziwei & Matus Telgarsky. (2019). The implicit bias of gradient descent on nonseparable data. Conference on Learning Theory. 1772–1798. 14 indexed citations

7.

Ji, Ziwei & Matus Telgarsky. (2019). Gradient descent aligns the layers of deep linear networks. International Conference on Learning Representations. 15 indexed citations

8.

Abernethy, Jacob, Sébastien Lahaie, & Matus Telgarsky. (2016). Rate of Price Discovery in Iterative Combinatorial Auctions. 809–809. 1 indexed citations

9.

Anandkumar, Animashree, Rong Ge, Daniel Hsu, Sham M. Kakade, & Matus Telgarsky. (2014). Tensor decompositions for learning latent variable models. Journal of Machine Learning Research. 15(1). 2773–2832. 371 indexed citations breakdown →

10.

Agarwal, Alekh, Alina Beygelzimer, Daniel Hsu, John Langford, & Matus Telgarsky. (2014). Scalable Nonlinear Learning with Adaptive Polynomial Expansions. arXiv (Cornell University). 1 indexed citations

11.

Dasgupta, Sanjoy & Matus Telgarsky. (2012). Agglomerative Bregman Clustering. International Conference on Machine Learning. 1011–1018. 11 indexed citations

12.

Telgarsky, Matus. (2011). The Fast Convergence of Boosting. Neural Information Processing Systems. 24. 1593–1601. 1 indexed citations

13.

Telgarsky, Matus. (2011). The Convergence Rate of AdaBoost and Friends. arXiv (Cornell University). 1 indexed citations

14.

Telgarsky, Matus & Andrea Vattani. (2010). Hartigan's method: κ-means clustering without Voronoi. Journal of Machine Learning Research. 9. 820–827. 20 indexed citations

15.

Telgarsky, Matus & Andrea Vattani. (2010). Hartigan's Method: k-means Clustering without Voronoi. International Conference on Artificial Intelligence and Statistics. 820–827. 19 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