Martin Jaggi

13.1k total citations · 1 hit paper
78 papers, 2.0k citations indexed

About

Martin Jaggi is a scholar working on Artificial Intelligence, Computational Mechanics and Computer Vision and Pattern Recognition. According to data from OpenAlex, Martin Jaggi has authored 78 papers receiving a total of 2.0k indexed citations (citations by other indexed papers that have themselves been cited), including 56 papers in Artificial Intelligence, 18 papers in Computational Mechanics and 13 papers in Computer Vision and Pattern Recognition. Recurrent topics in Martin Jaggi's work include Stochastic Gradient Optimization Techniques (28 papers), Sparse and Compressive Sensing Techniques (17 papers) and Topic Modeling (14 papers). Martin Jaggi is often cited by papers focused on Stochastic Gradient Optimization Techniques (28 papers), Sparse and Compressive Sensing Techniques (17 papers) and Topic Modeling (14 papers). Martin Jaggi collaborates with scholars based in Switzerland, United States and Germany. Martin Jaggi's co-authors include Sebastian U. Stich, Martin Takáč, Sai Praneeth Karimireddy, Michael I. Jordan, Virginia Smith, Claudiu Musat, Thomas Hofmann, Valéria De Luca, Chenxin Ma and Katerina Argyraki and has published in prestigious journals such as SHILAP Revista de lepidopterología, Journal of Machine Learning Research and SIAM Journal on Optimization.

In The Last Decade

Martin Jaggi

72 papers receiving 1.9k citations

Hit Papers

Revisiting Frank-Wolfe: Projection-Free Sparse Convex Opt... 2013 2026 2017 2021 2013 100 200 300

Peers — A (Enhanced Table)

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

Name h Career Trend Papers Cites
Martin Jaggi Switzerland 22 1.3k 438 405 321 196 78 2.0k
Rie Johnson United States 10 1.8k 1.3× 301 0.7× 421 1.0× 168 0.5× 85 0.4× 12 2.3k
Jason D. Lee United States 20 933 0.7× 269 0.6× 335 0.8× 234 0.7× 76 0.4× 61 1.7k
Ohad Shamir Israel 26 2.0k 1.5× 506 1.2× 661 1.6× 469 1.5× 188 1.0× 69 2.7k
Yiming Ying United States 25 1.3k 1.0× 996 2.3× 664 1.6× 152 0.5× 78 0.4× 77 2.6k
Prateek Jain India 20 422 0.3× 637 1.5× 709 1.8× 138 0.4× 300 1.5× 97 2.0k
Gautam Shroff India 18 863 0.6× 137 0.3× 138 0.3× 416 1.3× 133 0.7× 83 1.8k
Praneeth Netrapalli United States 15 364 0.3× 262 0.6× 516 1.3× 112 0.3× 101 0.5× 44 1.1k
Karthik Sridharan United States 19 1.3k 0.9× 609 1.4× 354 0.9× 164 0.5× 77 0.4× 47 1.8k
Ding Zhou China 14 713 0.5× 330 0.8× 331 0.8× 69 0.2× 42 0.2× 30 1.4k
Tamás Linder Canada 24 691 0.5× 689 1.6× 265 0.7× 672 2.1× 534 2.7× 143 1.9k

Countries citing papers authored by Martin Jaggi

Since Specialization
Citations

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

Fields of papers citing papers by Martin Jaggi

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

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

Co-authorship network of co-authors of Martin Jaggi

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

All Works

20 of 20 papers shown
1.
Karimireddy, Sai Praneeth, et al.. (2024). MyThisYourThat for interpretable identification of systematic bias in federated learning for biomedical images. npj Digital Medicine. 7(1). 238–238.
2.
Zhang, Jian, Mickael L. Perrin, Luis Barba, et al.. (2022). High-speed identification of suspended carbon nanotubes using Raman spectroscopy and deep learning. Microsystems & Nanoengineering. 8(1). 19–19. 17 indexed citations
3.
Karimireddy, Sai Praneeth, Martin Jaggi, Satyen Kale, et al.. (2021). Breaking the centralized barrier for cross-device federated learning. Neural Information Processing Systems. 34. 25 indexed citations
4.
Shokri‐Ghadikolaei, Hossein, Sebastian U. Stich, & Martin Jaggi. (2021). LENA: Communication-Efficient Distributed Learning with Self-Triggered Gradient Uploads. Infoscience (Ecole Polytechnique Fédérale de Lausanne). 130. 3943–3951. 1 indexed citations
5.
Yu, Kaicheng, et al.. (2020). Evaluating The Search Phase of Neural Architecture Search. Infoscience (Ecole Polytechnique Fédérale de Lausanne). 55 indexed citations
6.
Pedregosa, Fabián, et al.. (2020). Linearly Convergent Frank-Wolfe without Line-Search.. International Conference on Artificial Intelligence and Statistics. 1–10.
7.
Lin, Tao, Lingjing Kong, Sebastian U. Stich, & Martin Jaggi. (2020). Ensemble Distillation for Robust Model Fusion in Federated Learning. Infoscience (Ecole Polytechnique Fédérale de Lausanne). 33. 2351–2363. 3 indexed citations
8.
Vogels, Thijs, Sai Praneeth Karimireddy, & Martin Jaggi. (2020). Practical Low-Rank Communication Compression in Decentralized Deep Learning. Infoscience (Ecole Polytechnique Fédérale de Lausanne). 33. 14171–14181. 14 indexed citations
9.
Mai, Florian, et al.. (2019). On the Tunability of Optimizers in Deep Learning. Infoscience (Ecole Polytechnique Fédérale de Lausanne). 4 indexed citations
10.
Vogels, Thijs, Sai Praneeth Karimireddy, & Martin Jaggi. (2019). PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization. Infoscience (Ecole Polytechnique Fédérale de Lausanne). 32. 14236–14245. 15 indexed citations
11.
Lin, T., et al.. (2018). End-to-End DNN Training with Block Floating Point Arithmetic. arXiv (Cornell University). 6 indexed citations
12.
Pedregosa, Fabián, et al.. (2018). Step-Size Adaptivity in Projection-Free Optimization. arXiv (Cornell University). 3 indexed citations
13.
Karimireddy, Sai Praneeth, Sebastian U. Stich, & Martin Jaggi. (2018). Adaptive balancing of gradient and update computation times using global geometry and approximate subproblems. Infoscience (Ecole Polytechnique Fédérale de Lausanne). 1204–1213. 1 indexed citations
14.
Jaggi, Martin, et al.. (2018). COLA: Communication-Efficient Decentralized Linear Learning. arXiv (Cornell University). 4537–4547. 1 indexed citations
15.
Musat, Claudiu, et al.. (2018). EmbedRank: Unsupervised Keyphrase Extraction using Sentence Embeddings.. arXiv (Cornell University). 13 indexed citations
16.
Lacoste-Julien, Simon, Martin Jaggi, Mark Schmidt, & Patrick Pletscher. (2013). Block-Coordinate Frank-Wolfe Optimization for Structural SVMs. Infoscience (Ecole Polytechnique Fédérale de Lausanne). 24 indexed citations
17.
Jaggi, Martin. (2013). Revisiting Frank-Wolfe: Projection-Free Sparse Convex Optimization. Infoscience (Ecole Polytechnique Fédérale de Lausanne). 7(1). 427–435. 363 indexed citations breakdown →
18.
Giesen, Joachim, et al.. (2012). Regularization Paths with Guarantees for Convex Semidefinite Optimization.. Infoscience (Ecole Polytechnique Fédérale de Lausanne). 432–439. 9 indexed citations
19.
Lacoste-Julien, Simon, Martin Jaggi, Mark Schmidt, & Patrick Pletscher. (2012). Stochastic Block-Coordinate Frank-Wolfe Optimization for Structural SVMs. arXiv (Cornell University). 9 indexed citations
20.
Jaggi, Martin, et al.. (2010). A Simple Algorithm for Nuclear Norm Regularized Problems. Infoscience (Ecole Polytechnique Fédérale de Lausanne). 471–478. 112 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

Rankless by CCL
2026