Sham Kakade

{{Infobox scientist | name = Sham Machandranath Kakade | field = Computer Science, Artificial Intelligence | work_institution = Toyota Technological Institute at Chicago Wharton Microsoft Research University of Washington Harvard University | alma_mater = Caltech University College London<ref name="bio">{{cite web|url=https://sham.seas.harvard.edu/|title=Sham Machandranath Kakade|accessdate=2019-04-25}}</ref> | 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.<ref name=":0">{{Cite web |title=Sham Kakade {{!}} Harvard John A. Paulson School of Engineering and Applied Sciences |url=https://seas.harvard.edu/person/sham-kakade |access-date=2026-04-07 |website=seas.harvard.edu}}</ref> Kakade is a co-director of the Kempner Institute for the Study of Natural and Artificial Intelligence. <ref name=":1">{{Cite web |title=Sham Kakade |url=https://kempnerinstitute.harvard.edu/people/our-people/sham-kakade/ |access-date=2026-04-07 |website=Kempner Institute |language=en-US}}</ref><ref name=":2">{{Cite web |last=chadcampbell |date=2022-09-23 |title=Science, Tech and AI Leaders Convene to Launch Kempner Institute |url=https://chanzuckerberg.com/newsroom/science-tech-and-ai-leaders-convene-to-launch-kempner-institute/ |access-date=2026-04-07 |website=Chan Zuckerberg Initiative |language=en-US}}</ref> He co-founded the Algorithmic Foundations of Data Science Institute.<ref>{{cite web|url=https://www.nsf.gov/news/news_summ.jsp?cntn_id=242888|website=National Science Foundation|accessdate=25 April 2019|title=New NSF awards will bring together cross-disciplinary science communities to develop foundations of data science}}</ref>

== 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.<ref name=":2" /> 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. <ref name=":2" />

== Research == Kakade's research includes work on Reinforcement Learning, Tensor-Algebraic methods, and Convex optimization. <ref name=":1" />

=== Reinforcement Learning === Kakade's doctoral work helped established statistical frameworks used in the study of sample complexity in reinforcement learning. <ref name=":0" /> He co-developed methods in policy optimization, including early work on natural policy gradient, conservative policy iteration. <ref>{{Cite web |title=Sham Kakade |url=https://l4dc.lids.mit.edu/speaker/sham-kakade/ |access-date=2026-04-07 |website=l4dc.lids.mit.edu}}</ref><ref name=":3">{{Cite web |title=Symposium Fall 2020 - MINDS Plenary Sham Kakade (2020-10-23) |url=https://www.minds.jhu.edu/event/symposium-fall-2020-minds-plenary-sham-kakade/ |access-date=2026-04-07 |language=en-US}}</ref> Kakade has contributed to theoretical analyses of reinforcement learning algorithms with provable performance guarantees. <ref name=":3" />

=== Bandit Models === Kakade has worked extensively on multi-armed and structured bandit models, including linear and Gaussian process-based bandit.<ref name=":0" /> <ref>{{Cite web |title=Seminar @ Cornell Tech: Sham Kakade |url=https://tech.cornell.edu/events/seminar-cornell-tech-sham-kakade/ |access-date=2026-04-08 |website=Cornell Tech |language=en}}</ref> 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. <ref>{{Cite web |title=Symposium Fall 2020 - MINDS Plenary Sham Kakade (2020-10-23) |url=https://www.minds.jhu.edu/event/symposium-fall-2020-minds-plenary-sham-kakade/ |access-date=2026-04-08 |language=en-US}}</ref><ref name=":4">{{Citation |last=Srinivas |first=Niranjan |title=Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design |date=2010-06-09 |url=http://arxiv.org/abs/0912.3995 |access-date=2026-04-08 |publisher=arXiv |doi=10.48550/arXiv.0912.3995 |id=arXiv:0912.3995 |last2=Krause |first2=Andreas |last3=Kakade |first3=Sham M. |last4=Seeger |first4=Matthias}}</ref> The work established regret bounds connected to information gain in Gaussian process models. <ref name=":4" />

=== 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. <ref name=":0" />

== 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." <ref name=":4" /> <ref name=":5">{{Cite web |title=ICML Test Of Time Test of Time: Gaussian Process Optimization in the Bandit Settings: No Regret and Experimental Design |url=https://icml.cc/virtual/2020/test-of-time/7965 |access-date=2026-04-08 |website=icml.cc}}</ref><ref>{{Cite web |title=Prof. Andreas Krause receives ICML Test of Time Award |url=https://inf.ethz.ch/news-and-events/spotlights/2020/07/krause-test-of-time.html |access-date=2026-04-08 |website=Department of Computer Science |language=en}}</ref> The ICML awards committee cited the paper's influential role in connecting Gaussian process models, bandit optimization, and experimental design. <ref name=":5" />

He was a recipient of the INFORMS Revenue Management and Pricing section Prize in 2014. <ref>{{Cite web |title=Section Award - Revenue Management and Pricing Section |url=https://connect.informs.org/rmp/awards/current-awards/section-award |access-date=2026-04-08 |website=connect.informs.org}}</ref> Kakade has served on the Alfred P. Sloan Foundation's selection committee for the Computer Science Sloan Research Fellowships. <ref>{{Cite web |title=Past Selection Committee Members |url=https://sloan.org/fellowships/about-fellowships/past-cmte-members |access-date=2026-04-08 |website=sloan.org |language=en}}</ref>

==References== {{Reflist}}

== External links == * [https://sham.seas.harvard.edu Sham Kakade's home page] * [https://zenodo.org/record/5120004#.Yq_yUC-B1pR MusicNet]

{{DEFAULTSORT:Kakade, Sham}} Category:American computer scientists Category:Harvard University faculty Category:Alumni of University College London Category:California Institute of Technology alumni Category:Year of birth missing (living people) Category:Living people Category:Toyota Technological Institute at Chicago faculty