James Martens

8.4k total citations · 3 hit papers
23 papers, 3.5k citations indexed

About

James Martens is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition and Statistical and Nonlinear Physics. According to data from OpenAlex, James Martens has authored 23 papers receiving a total of 3.5k indexed citations (citations by other indexed papers that have themselves been cited), including 18 papers in Artificial Intelligence, 12 papers in Computer Vision and Pattern Recognition and 8 papers in Statistical and Nonlinear Physics. Recurrent topics in James Martens's work include Model Reduction and Neural Networks (8 papers), Neural Networks and Applications (6 papers) and Stochastic Gradient Optimization Techniques (6 papers). James Martens is often cited by papers focused on Model Reduction and Neural Networks (8 papers), Neural Networks and Applications (6 papers) and Stochastic Gradient Optimization Techniques (6 papers). James Martens collaborates with scholars based in Canada, United States and Australia. James Martens's co-authors include Ilya Sutskever, Geoffrey E. Hinton, George E. Dahl, Roger Grosse, Jimmy Ba, Qinghua Lu, Salil S. Kanhere, Hye-Young Paik, Richard S. Zemel and Jakob Foerster and has published in prestigious journals such as Journal of Machine Learning Research, Biological Cybernetics and Trends in Cardiovascular Medicine.

In The Last Decade

James Martens

23 papers receiving 3.3k citations

Hit Papers

On the importance of initialization and momentum in deep ... 2010 2026 2015 2020 2013 2011 2010 500 1000 1.5k

Peers — A (Enhanced Table)

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

Name h Career Trend Papers Cites
James Martens Canada 13 2.0k 1.3k 394 308 241 23 3.5k
豊 松尾 3 1.7k 0.8× 1.5k 1.2× 296 0.8× 277 0.9× 166 0.7× 5 3.6k
Tapani Raiko Finland 22 1.5k 0.7× 1.2k 0.9× 350 0.9× 221 0.7× 137 0.6× 61 3.2k
Sanjoy Dasgupta United States 31 2.4k 1.2× 1.1k 0.9× 525 1.3× 244 0.8× 388 1.6× 89 4.2k
Nojun Kwak South Korea 29 1.9k 0.9× 2.3k 1.8× 522 1.3× 233 0.8× 367 1.5× 151 4.4k
Dong Huang China 38 2.2k 1.1× 2.7k 2.1× 275 0.7× 297 1.0× 221 0.9× 175 4.6k
Ethem Alpaydın Türkiye 24 1.6k 0.8× 1.3k 1.0× 293 0.7× 162 0.5× 146 0.6× 80 3.1k
Joan Bruna United States 17 1.4k 0.7× 1.4k 1.1× 289 0.7× 204 0.7× 539 2.2× 47 3.7k
P. A. Estévez Chile 28 1.4k 0.7× 923 0.7× 394 1.0× 358 1.2× 118 0.5× 131 3.5k
Vincent Dumoulin United States 10 1.5k 0.8× 2.1k 1.7× 467 1.2× 271 0.9× 154 0.6× 15 4.8k
Miguel Á. Carreira-Perpiñán United States 27 1.3k 0.7× 1.8k 1.4× 393 1.0× 284 0.9× 200 0.8× 106 3.4k

Countries citing papers authored by James Martens

Since Specialization
Citations

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

Fields of papers citing papers by James Martens

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

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

Co-authorship network of co-authors of James Martens

This figure shows the co-authorship network connecting the top 25 collaborators of James Martens. A scholar is included among the top collaborators of James Martens 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 James Martens. James Martens 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.
Martens, James. (2020). New Insights and Perspectives on the Natural Gradient Method. Journal of Machine Learning Research. 21(146). 1–76. 76 indexed citations
2.
Zhang, Guodong, James Martens, & Roger Grosse. (2019). Fast Convergence of Natural Gradient Descent for Over-Parameterized Neural Networks. arXiv (Cornell University). 32. 8080–8091. 5 indexed citations
3.
Qin, Chongli, James Martens, Sven Gowal, et al.. (2019). Adversarial Robustness through Local Linearization. Neural Information Processing Systems. 32. 13824–13833. 27 indexed citations
4.
Balduzzi, David, Sébastien Racanière, James Martens, et al.. (2019). Differentiable Game Mechanics. Journal of Machine Learning Research. 20(84). 1–40. 6 indexed citations
5.
Balduzzi, David, Sébastien Racanière, James Martens, et al.. (2018). The Mechanics of n-Player Differentiable Games. UCL Discovery (University College London). 354–363. 13 indexed citations
6.
Martens, James, et al.. (2018). Kronecker-factored Curvature Approximations for Recurrent Neural Networks. International Conference on Learning Representations. 13 indexed citations
7.
Nado, Zachary, et al.. (2018). STOCHASTIC GRADIENT LANGEVIN DYNAMICS THAT EXPLOIT NEURAL NETWORK STRUCTURE. International Conference on Learning Representations. 4 indexed citations
8.
Ba, Jimmy, Roger Grosse, & James Martens. (2017). Distributed Second-Order Optimization using Kronecker-Factored Approximations. International Conference on Learning Representations. 24 indexed citations
9.
Martens, James & Roger Grosse. (2015). Optimizing Neural Networks with Kronecker-factored Approximate Curvature. International Conference on Machine Learning. 2408–2417. 29 indexed citations
10.
Sutskever, Ilya, James Martens, George E. Dahl, & Geoffrey E. Hinton. (2013). On the importance of initialization and momentum in deep learning. International Conference on Machine Learning. 1139–1147. 1893 indexed citations breakdown →
11.
Martens, James, et al.. (2013). On the Representational Efficiency of Restricted Boltzmann Machines. neural information processing systems. 26. 2877–2885. 11 indexed citations
12.
Martens, James, Arkadev Chattopadhyay, Toniann Pitassi, & Richard S. Zemel. (2013). On the Expressive Power of Restricted Boltzmann Machines.. Neural Information Processing Systems. 2877–2885. 4 indexed citations
13.
Martens, James & Ilya Sutskever. (2011). Learning Recurrent Neural Networks with Hessian-Free Optimization. International Conference on Machine Learning. 1033–1040. 300 indexed citations
14.
Sutskever, Ilya, James Martens, & Geoffrey E. Hinton. (2011). Generating Text with Recurrent Neural Networks. International Conference on Machine Learning. 1017–1024. 626 indexed citations breakdown →
15.
Eliasmith, Chris & James Martens. (2011). Normalization for probabilistic inference with neurons. Biological Cybernetics. 104(4-5). 251–262. 3 indexed citations
16.
Martens, James. (2010). Deep learning via Hessian-free optimization. International Conference on Machine Learning. 735–742. 343 indexed citations breakdown →
17.
Martens, James. (2010). Learning the Linear Dynamical System with ASOS. International Conference on Machine Learning. 743–750. 6 indexed citations
18.
Martens, James & Ilya Sutskever. (2010). Parallelizable Sampling of Markov Random Fields. International Conference on Artificial Intelligence and Statistics. 517–524. 8 indexed citations
19.
Graovac, M., et al.. (2007). Novel Lead Configurations for Robust Bio-Impedance Acquisition. Conference proceedings. 17. 2764–2767. 2 indexed citations
20.
Martens, James. (1999). Modulation of Kv Channel α/β Subunit Interactions. Trends in Cardiovascular Medicine. 9(8). 253–258. 89 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