Biography:Sham Kakade
Sham Machandranath Kakade | |
|---|---|
| Alma mater | Caltech University College London[1] |
| Scientific career | |
| Fields | Computer Science, Artificial Intelligence |
| Institutions | Toyota Technological Institute at Chicago Wharton Microsoft Research University of Washington Harvard University |
| Doctoral advisor | Peter Dayan |
Sham Machandranath Kakade is an American computer scientist. He is a Gordon McKay Professor in Computer Science at Harvard University, with a joint appointment in the Department of Statistics.[2] Kakade is a co-director of the Kempner Institute for the Study of Natural and Artificial Intelligence. [3][4] He co-founded the Algorithmic Foundations of Data Science Institute.[5]
Education and Career
Kakade earned a Bachelor of Science in Physics from the California Institute of Technology and a PhD from the Gatsby Computational Neuroscience Unit at University College London, under the supervision of Peter Dayan.[4] Prior to his current position at Harvard, he served as a Principal Researcher at Microsoft Research, an assistant professor at the Toyota Technological Institute at Chicago and Wharton, and a professor at the University of Washington. [4]
Research
Kakade's research includes work on Reinforcement Learning, Tensor-Algebraic methods, and Convex optimization. [3]
Reinforcement Learning
Kakade's doctoral work helped established statistical frameworks used in the study of sample complexity in reinforcement learning. [2] He co-developed methods in policy optimization, including early work on natural policy gradient, conservative policy iteration. [6][7] Kakade has contributed to theoretical analyses of reinforcement learning algorithms with provable performance guarantees. [7]
Bandit Models
Kakade has worked extensively on multi-armed and structured bandit models, including linear and Gaussian process-based bandit.[2] [8] He co-authored "Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design," which studied Gaussian process methods in a nonparametric bandit setting. [9][10] The work established regret bounds connected to information gain in Gaussian process models. [10]
Optimization
Kakade has studied convex optimization and non-covex optimization in machine learning. His work includes the analysis of optimization algorithms for escaping saddle points in non-convex problems. He has also co-authored research on optimization methods used in modern machine learning system. [2]
Awards
Kakade was a co-recipient of the Test of Time Award at the International Conference on Machine Learning (ICML) in 2020 for the paper "Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design." [10] [11][12] The ICML awards committee cited the paper's influential role in connecting Gaussian process models, bandit optimization, and experimental design. [11]
He was a recipient of the INFORMS Revenue Management and Pricing section Prize in 2014. [13] Kakade has served on the Alfred P. Sloan Foundation's selection committee for the Computer Science Sloan Research Fellowships. [14]
References
- ↑ "Sham Machandranath Kakade". https://sham.seas.harvard.edu/. Retrieved 2019-04-25.
- ↑ 2.0 2.1 2.2 2.3 "Sham Kakade | Harvard John A. Paulson School of Engineering and Applied Sciences". https://seas.harvard.edu/person/sham-kakade.
- ↑ 3.0 3.1 "Sham Kakade" (in en-US). https://kempnerinstitute.harvard.edu/people/our-people/sham-kakade/.
- ↑ 4.0 4.1 4.2 chadcampbell (2022-09-23). "Science, Tech and AI Leaders Convene to Launch Kempner Institute" (in en-US). https://chanzuckerberg.com/newsroom/science-tech-and-ai-leaders-convene-to-launch-kempner-institute/.
- ↑ "New NSF awards will bring together cross-disciplinary science communities to develop foundations of data science". https://www.nsf.gov/news/news_summ.jsp?cntn_id=242888. Retrieved 25 April 2019.
- ↑ "Sham Kakade". https://l4dc.lids.mit.edu/speaker/sham-kakade/.
- ↑ 7.0 7.1 "Symposium Fall 2020 - MINDS Plenary Sham Kakade (2020-10-23)" (in en-US). https://www.minds.jhu.edu/event/symposium-fall-2020-minds-plenary-sham-kakade/.
- ↑ "Seminar @ Cornell Tech: Sham Kakade" (in en). https://tech.cornell.edu/events/seminar-cornell-tech-sham-kakade/.
- ↑ "Symposium Fall 2020 - MINDS Plenary Sham Kakade (2020-10-23)" (in en-US). https://www.minds.jhu.edu/event/symposium-fall-2020-minds-plenary-sham-kakade/.
- ↑ 10.0 10.1 10.2 Srinivas, Niranjan; Krause, Andreas; Kakade, Sham M.; Seeger, Matthias (2010-06-09), Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design, arXiv, doi:10.48550/arXiv.0912.3995, arXiv:0912.3995, http://arxiv.org/abs/0912.3995, retrieved 2026-04-08
- ↑ 11.0 11.1 "ICML Test Of Time Test of Time: Gaussian Process Optimization in the Bandit Settings: No Regret and Experimental Design". https://icml.cc/virtual/2020/test-of-time/7965.
- ↑ "Prof. Andreas Krause receives ICML Test of Time Award" (in en). https://inf.ethz.ch/news-and-events/spotlights/2020/07/krause-test-of-time.html.
- ↑ "Section Award - Revenue Management and Pricing Section". https://connect.informs.org/rmp/awards/current-awards/section-award.
- ↑ "Past Selection Committee Members" (in en). https://sloan.org/fellowships/about-fellowships/past-cmte-members.
External links
 |  |
