Search the dblp DataBase

Publications of Author

1. Sham M. Kakade, Michael J. Kearns
   Trading in Markovian Price Models. [Citation Graph (0, 0)][DBLP]
   COLT, 2005, pp:606-620 [Conf]
   
2. Eyal Even-Dar, Sham M. Kakade, Yishay Mansour
   Reinforcement Learning in POMDPs Without Resets. [Citation Graph (0, 0)][DBLP]
   IJCAI, 2005, pp:690-695 [Conf]
   
3. Eyal Even-Dar, Sham M. Kakade, Yishay Mansour
   The Value of Observation for Monitoring Dynamic Systems. [Citation Graph (0, 0)][DBLP]
   IJCAI, 2007, pp:2474-2479 [Conf]
   
4. Eyal Even-Dar, Sham M. Kakade, Yishay Mansour
   Experts in a Markov Decision Process. [Citation Graph (0, 0)][DBLP]
   NIPS, 2004, pp:- [Conf]
   
5. Sham M. Kakade, Adam Kalai
   From Batch to Transductive Online Learning. [Citation Graph (0, 0)][DBLP]
   NIPS, 2005, pp:- [Conf]
   
6. Sham M. Kakade, Michael J. Kearns, Luis E. Ortiz, Robin Pemantle, Siddharth Suri
   Economic Properties of Social Networks. [Citation Graph (0, 0)][DBLP]
   NIPS, 2004, pp:- [Conf]
   
7. Sham M. Kakade, Andrew Y. Ng
   Online Bounds for Bayesian Algorithms. [Citation Graph (0, 0)][DBLP]
   NIPS, 2004, pp:- [Conf]
   
8. Sham M. Kakade, Matthias Seeger, Dean P. Foster
   Worst-Case Bounds for Gaussian Process Models. [Citation Graph (0, 0)][DBLP]
   NIPS, 2005, pp:- [Conf]
   
9. Eyal Even-Dar, Sham M. Kakade, Michael S. Kearns, Yishay Mansour
   (In)Stability properties of limit order dynamics. [Citation Graph (0, 0)][DBLP]
   ACM Conference on Electronic Commerce, 2006, pp:120-129 [Conf]
   
10. Sham M. Kakade, Dean P. Foster
    Multi-view Regression Via Canonical Correlation Analysis. [Citation Graph (0, 0)][DBLP]
    COLT, 2007, pp:82-96 [Conf]
    
11. Sham M. Kakade, Adam Tauman Kalai, Katrina Ligett
    Playing games with approximation algorithms. [Citation Graph (0, 0)][DBLP]
    STOC, 2007, pp:546-555 [Conf]
    
12. Eyal Even-Dar, Sham M. Kakade, Yishay Mansour
    Planning in POMDPs Using Multiplicity Automata. [Citation Graph (0, 0)][DBLP]
    UAI, 2005, pp:185-192 [Conf]
    
13. 
    An Information Theoretic Framework for Multi-view Learning. [Citation Graph (, )][DBLP]
    
    
14. 
    Stochastic Linear Optimization under Bandit Feedback. [Citation Graph (, )][DBLP]
    
    
15. 
    Efficient bandit algorithms for online multiclass prediction. [Citation Graph (, )][DBLP]
    
    
16. 
    Multi-view clustering via canonical correlation analysis. [Citation Graph (, )][DBLP]
    
    
17. 
    On the Complexity of Linear Prediction: Risk Bounds, Margin Bounds, and Regularization. [Citation Graph (, )][DBLP]
    
    
18. 
    On the Generalization Ability of Online Strongly Convex Programming Algorithms. [Citation Graph (, )][DBLP]
    
    
19. 
    Mind the Duality Gap: Logarithmic regret algorithms for online optimization. [Citation Graph (, )][DBLP]
    
    
20. 
    The price of truthfulness for pay-per-click auctions. [Citation Graph (, )][DBLP]
    
    
21. 
    A Spectral Algorithm for Learning Hidden Markov Models [Citation Graph (, )][DBLP]
    
    
22. 
    Multi-Label Prediction via Compressed Sensing [Citation Graph (, )][DBLP]
    
    
23. 
    Applications of strong convexity--strong smoothness duality to learning with matrices [Citation Graph (, )][DBLP]
    
    
24. 
    Learning Exponential Families in High-Dimensions: Strong Convexity and Sparsity [Citation Graph (, )][DBLP]
    
    
25. 
    Gaussian Process Bandits without Regret: An Experimental Design Approach [Citation Graph (, )][DBLP]
    
    
26. 
    An Optimal Dynamic Mechanism for Multi-Armed Bandit Processes [Citation Graph (, )][DBLP]
    
    
27. 
    Learning from Logged Implicit Exploration Data [Citation Graph (, )][DBLP]