Sham M Kakade
TitleCited byYear
Gaussian process optimization in the bandit setting: No regret and experimental design
N Srinivas, A Krause, SM Kakade, M Seeger
arXiv preprint arXiv:0912.3995, 2009
8462009
Cover trees for nearest neighbor
A Beygelzimer, S Kakade, J Langford
Proceedings of the 23rd international conference on Machine learning, 97-104, 2006
7812006
Opponent interactions between serotonin and dopamine
ND Daw, S Kakade, P Dayan
Neural Networks 15 (4-6), 603-616, 2002
7352002
Tensor decompositions for learning latent variable models
A Anandkumar, R Ge, D Hsu, SM Kakade, M Telgarsky
The Journal of Machine Learning Research 15 (1), 2773-2832, 2014
7312014
A natural policy gradient
S Kakade
Advances in neural information processing systems 14, 1531-1538, 2001
5992001
Multi-view clustering via canonical correlation analysis
K Chaudhuri, SM Kakade, K Livescu, K Sridharan
Proceedings of the 26th annual international conference on machine learning …, 2009
5602009
A spectral algorithm for learning hidden markov models
D Hsu, SM Kakade, T Zhang
Journal of Computer and System Sciences, 2012
4312012
Learning and selective attention
P Dayan, S Kakade, PR Montague
nature neuroscience 3 (11s), 1218, 2000
4252000
Multi-label prediction via compressed sensing
DJ Hsu, SM Kakade, J Langford, T Zhang
Advances in neural information processing systems, 772-780, 2009
3962009
Stochastic linear optimization under bandit feedback
V Dani, TP Hayes, SM Kakade
3912008
Dopamine: generalization and bonuses
S Kakade, P Dayan
Neural Networks 15 (4-6), 549-559, 2002
3842002
On the sample complexity of reinforcement learning
SM Kakade
University of London, 2003
3732003
Approximately optimal approximate reinforcement learning
S Kakade, J Langford
MACHINE LEARNING-INTERNATIONAL WORKSHOP THEN CONFERENCE-, 267-274, 2002
3032002
Information-theoretic regret bounds for gaussian process optimization in the bandit setting
N Srinivas, A Krause, SM Kakade, MW Seeger
IEEE Transactions on Information Theory 58 (5), 3250-3265, 2012
2912012
Information-Theoretic Regret Boundsfor Gaussian Process Optimization in the Bandit Setting
N Srinivas, A Krause, S Kakade, M Seeger
Information Theory, IEEE Transactions on, 1-1, 2011
2912011
How to escape saddle points efficiently
C Jin, R Ge, P Netrapalli, SM Kakade, MI Jordan
Proceedings of the 34th International Conference on Machine Learning-Volume …, 2017
2772017
A method of moments for mixture models and hidden Markov models
A Anandkumar, D Hsu, SM Kakade
Conference on Learning Theory, 33.1-33.34, 2012
2592012
Learning mixtures of spherical gaussians: moment methods and spectral decompositions
D Hsu, SM Kakade
Proceedings of the 4th conference on Innovations in Theoretical Computer …, 2013
2562013
A spectral algorithm for latent dirichlet allocation
A Anandkumar, DP Foster, DJ Hsu, SM Kakade, YK Liu
Advances in Neural Information Processing Systems, 917-925, 2012
2432012
A spectral algorithm for latent dirichlet allocation
A Anandkumar, DP Foster, DJ Hsu, SM Kakade, YK Liu
Advances in Neural Information Processing Systems, 917-925, 2012
2432012
The system can't perform the operation now. Try again later.
Articles 1–20