Sotabase

Career

· Professor, Harvard University2022–
· Co-director, Kempner Institute at Harvard University2022–
· Professor, University of Washington2015–2021
· Bachelor of Science - BS, Physics, Caltech
· Doctor of Philosophy - PhD, Computer Science, UCL

Publications (306)

Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting
IEEE Transactions on Information Theory · 2009
1,723
cited
A Natural Policy Gradient
Neural Information Processing Systems · 2001
1,341
cited
Approximately Optimal Approximate Reinforcement Learning
International Conference on Machine Learning · 2002
1,229
cited
Tensor decompositions for learning latent variable models
Journal of machine learning research · 2012
1,190
cited
Cover trees for nearest neighbor
International Conference on Machine Learning · 2006
967
cited
Meta-Learning with Implicit Gradients
Neural Information Processing Systems · 2019
947
cited
Stochastic Linear Optimization under Bandit Feedback
Annual Conference Computational Learning Theory · 2008
934
cited
How to Escape Saddle Points Efficiently
International Conference on Machine Learning · 2017
903
cited
Robust Aggregation for Federated Learning
IEEE Transactions on Signal Processing · 2019
873
cited
Opponent interactions between serotonin and dopamine
Neural Networks · 2002
850
cited
Multi-view clustering via canonical correlation analysis
International Conference on Machine Learning · 2009
830
cited
On the sample complexity of reinforcement learning.
2003
731
cited
Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator
International Conference on Machine Learning · 2018
666
cited
On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift
Journal of machine learning research · 2019
585
cited
Learning and selective attention
Nature Neuroscience · 2000
503
cited
Dopamine: generalization and bonuses
Neural Networks · 2002
469
cited
Multi-Label Prediction via Compressed Sensing
Neural Information Processing Systems · 2009
440
cited
A tail inequality for quadratic forms of subgaussian random vectors
arXiv.org · 2011
436
cited
On the Complexity of Linear Prediction: Risk Bounds, Margin Bounds, and Regularization
Neural Information Processing Systems · 2008
404
cited
A Method of Moments for Mixture Models and Hidden Markov Models
Annual Conference Computational Learning Theory · 2012
346
cited
Sotabase
Sham Kakade | Researcher Profile | Sotabase | Sotabase