Sham M. Kakade

19.7k total citations · 6 hit papers
121 papers, 7.4k citations indexed

About

Sham M. Kakade is a scholar working on Artificial Intelligence, Management Science and Operations Research and Computational Mechanics. According to data from OpenAlex, Sham M. Kakade has authored 121 papers receiving a total of 7.4k indexed citations (citations by other indexed papers that have themselves been cited), including 83 papers in Artificial Intelligence, 35 papers in Management Science and Operations Research and 20 papers in Computational Mechanics. Recurrent topics in Sham M. Kakade's work include Machine Learning and Algorithms (35 papers), Advanced Bandit Algorithms Research (30 papers) and Sparse and Compressive Sensing Techniques (20 papers). Sham M. Kakade is often cited by papers focused on Machine Learning and Algorithms (35 papers), Advanced Bandit Algorithms Research (30 papers) and Sparse and Compressive Sensing Techniques (20 papers). Sham M. Kakade collaborates with scholars based in United States, United Kingdom and Israel. Sham M. Kakade's co-authors include Peter Dayan, Daniel Hsu, John Langford, Matthias Seeger, Andreas Krause, Niranjan Srinivas, Karthik Sridharan, Nathaniel D. Daw, Alina Beygelzimer and Kamalika Chaudhuri and has published in prestigious journals such as Nature Neuroscience, Psychological Review and IEEE Transactions on Information Theory.

In The Last Decade

Sham M. Kakade

118 papers receiving 7.0k citations

Hit Papers

Opponent interactions between serotonin and dopamine 2002 2026 2010 2018 2002 2009 2012 2006 2009 100 200 300 400 500

Peers — A (Enhanced Table)

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

Name h Career Trend Papers Cites
Sham M. Kakade United States 41 3.6k 1.4k 1.4k 1.1k 703 121 7.4k
Richard S. Zemel Canada 41 6.5k 1.8× 526 0.4× 4.3k 3.1× 2.7k 2.6× 291 0.4× 149 13.7k
Naftali Tishby Israel 41 5.7k 1.6× 259 0.2× 1.8k 1.3× 1.1k 1.1× 599 0.9× 152 9.6k
Arthur Gretton Germany 35 3.9k 1.1× 225 0.2× 2.1k 1.5× 823 0.8× 246 0.3× 116 7.5k
Neil D. Lawrence United Kingdom 49 3.8k 1.1× 348 0.2× 1.8k 1.3× 235 0.2× 722 1.0× 172 8.4k
Robert A. Jacobs United States 38 4.9k 1.4× 324 0.2× 1.8k 1.3× 2.8k 2.7× 243 0.3× 120 11.1k
Jan Peters Germany 61 7.2k 2.0× 594 0.4× 2.6k 1.9× 1.8k 1.7× 1.2k 1.7× 414 14.8k
Bart Kosko United States 40 8.2k 2.3× 2.0k 1.4× 1.0k 0.7× 797 0.8× 622 0.9× 119 12.0k
Amit Konar India 40 3.5k 1.0× 246 0.2× 1.3k 1.0× 1.2k 1.1× 1.5k 2.1× 366 6.9k
Gail A. Carpenter United States 39 6.4k 1.8× 221 0.2× 2.2k 1.6× 2.3k 2.1× 462 0.7× 120 11.6k
Andy Barto 4 7.4k 2.1× 1.6k 1.1× 1.8k 1.3× 2.5k 2.4× 2.1k 3.0× 5 19.0k

Countries citing papers authored by Sham M. Kakade

Since Specialization
Citations

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

Fields of papers citing papers by Sham M. Kakade

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Sham M. Kakade. 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 Sham M. Kakade. The network helps show where Sham M. Kakade may publish in the future.

Co-authorship network of co-authors of Sham M. Kakade

This figure shows the co-authorship network connecting the top 25 collaborators of Sham M. Kakade. A scholar is included among the top collaborators of Sham M. Kakade 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 Sham M. Kakade. Sham M. Kakade 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.
Zou, Difan, Jingfeng Wu, Vladimir Braverman, et al.. (2021). The Benefits of Implicit Regularization from SGD in Least Squares Problems. arXiv (Cornell University). 34. 1 indexed citations
2.
Wang, Ruosong, et al.. (2021). An Exponential Lower Bound for Linearly Realizable MDP with Constant Suboptimality Gap. arXiv (Cornell University). 34. 1 indexed citations
3.
Agarwal, Alekh, Sham M. Kakade, Akshay Krishnamurthy, & Wen Sun. (2020). FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs. arXiv (Cornell University). 33. 20095–20107. 1 indexed citations
4.
Ge, Rong, Sham M. Kakade, Rahul Kidambi, & Praneeth Netrapalli. (2019). The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure.. arXiv (Cornell University). 6 indexed citations
5.
Jin, Chi, Praneeth Netrapalli, Rong Ge, Sham M. Kakade, & Michael I. Jordan. (2019). Stochastic Gradient Descent Escapes Saddle Points Efficiently.. arXiv (Cornell University). 19 indexed citations
6.
Bagnell, J. Andrew, Sham M. Kakade, Andrew Y. Ng, & Jeff Schneider. (2018). Policy Search by Dynamic Programming. ScholarlyCommons (University of Pennsylvania). 7 indexed citations
7.
Wu, Cathy, Aravind Rajeswaran, Yan Duan, et al.. (2018). Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines. arXiv (Cornell University). 5 indexed citations
8.
Jain, Prateek, Sham M. Kakade, Rahul Kidambi, Praneeth Netrapalli, & Aaron Sidford. (2018). Accelerating Stochastic Gradient Descent for Least Squares Regression. Conference on Learning Theory. 545–604. 5 indexed citations
9.
Kakade, Sham M., et al.. (2018). A Smoother Way to Train Structured Prediction Models. Neural Information Processing Systems. 31. 4766–4778. 1 indexed citations
10.
Jain, Prateek, Sham M. Kakade, Rahul Kidambi, Praneeth Netrapalli, & Aaron Sidford. (2016). Parallelizing Stochastic Approximation Through Mini-Batching and Tail-Averaging.. arXiv (Cornell University). 4 indexed citations
11.
Jin, Chi, Sham M. Kakade, & Praneeth Netrapalli. (2016). Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent. Neural Information Processing Systems. 29. 4520–4528. 15 indexed citations
12.
Belanger, David & Sham M. Kakade. (2015). A Linear Dynamical System Model for Text. International Conference on Machine Learning. 833–842. 4 indexed citations
13.
Anandkumar, Animashree, Rong Ge, Daniel Hsu, & Sham M. Kakade. (2014). A tensor approach to learning mixed membership community models. Journal of Machine Learning Research. 15(1). 2239–2312. 53 indexed citations
14.
Anandkumar, Animashree, Dean P. Foster, Daniel Hsu, Sham M. Kakade, & Yi-Kai Liu. (2012). Two SVDs Suffice: Spectral decompositions for probabilistic topic modeling and latent Dirichlet allocation. arXiv (Cornell University). 9 indexed citations
15.
Kakade, Sham M., et al.. (2010). Learning Exponential Families in High-Dimensions: Strong Convexity and Sparsity. ScholarlyCommons (University of Pennsylvania). 9. 381–388. 10 indexed citations
16.
Bartlett, Peter L., Varsha Dani, Thomas P. Hayes, et al.. (2008). High-probability regret bounds for bandit online linear optimization. QUT ePrints (Queensland University of Technology). 335–342. 32 indexed citations
17.
Hsu, Daniel, Sham M. Kakade, & Tong Zhang. (2008). A Spectral Algorithm for Learning Hidden Markov Models. arXiv (Cornell University). 71 indexed citations
18.
Kakade, Sham M. & Adam Tauman Kalai. (2005). From Batch to Transductive Online Learning. ScholarlyCommons (University of Pennsylvania). 18. 611–618. 8 indexed citations
19.
Kakade, Sham M. & Andrew Y. Ng. (2004). Online Bounds for Bayesian Algorithms. ScholarlyCommons (University of Pennsylvania). 17. 641–648. 24 indexed citations
20.
Kakade, Sham M., Yee Whye Teh, & Sam T. Roweis. (2002). An Alternate Objective Function for Markovian Fields. UCL Discovery (University College London). 275–282. 37 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