Sham Kakade
From Wikipedia, the free encyclopedia
University College London[1]
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]
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]
