Publications by Year

My Thesis

  • On the Sample Complexity of Reinforcement Learning.
    Sham Kakade.
    Gatsby Computational Neuroscience Unit.
    University College London, 2003.
    [abstract] [ps.gz] [pdf]

Preprints

  • On the Complexity of Linear Prediction: Risk Bounds, Margin Bounds, and Regularization
    Sham M. Kakade, Karthik Sridharan, & Ambuj Tewari.
    [pdf]

  • On the Generalization Ability of Online Strongly Convex Programming Algorithms
    Sham M. Kakade & Ambuj Tewari.
    [pdf]

2008

  • An Information Theoretic Framework for Multi-view Learning
    Karthik Sridharan & Sham M. Kakade.
    In COLT 2008.
    [pdf]

  • Stochastic Linear Optimization under Bandit Feedback
    Varsha Dani, Thomas Hayes, & Sham M. Kakade.
    In COLT 2008.
    [pdf]

  • High-Probability Regret Bounds for Bandit Online Linear Optimization
    Peter Bartlett, Varsha Dani, Thomas Hayes, Sham Kakade, Alexander Rakhlin & Ambuj Tewari.
    In COLT 2008.
    [pdf]

  • Efficient Bandit Algorithms for Online Multiclass Prediction
    Sham M. Kakade, Shai Shalev-Shwartz, & Ambuj Tewari.
    In the ICML 2008.
    [pdf]

  • Deterministic Calibration and Nash Equilibrium
    Sham M. Kakade & Dean P. Foster.
    In the J.C.S.S Learning Theory Special Issue 2008.
    [pdf]

  • Information Consistency of Nonparametric Gaussian Process Methods
    Matthias Seeger, Sham M. Kakade, & Dean P. Foster
    In IEEE Transactions on Information Theory, 2008.
    [pdf]

  • The Price of Bandit Information for Online Optimization
    Varsha Dani, Thomas Hayes, & Sham M. Kakade
    In Proceedings of NIPS, 2008.
    [pdf]

2007

  • Leveraging Archival Video for Building Face Datasets
    Deva Ramanan, Simon Baker & Sham M. Kakade
    In ICCV 2007.
    [pdf]

  • Playing Games with Approximation Algorithms
    Sham M. Kakade, Adam T. Kalai, & Katrina Ligett
    In STOC 2007.
    [pdf]

  • Multi-View Regression via Canonical Correlation Analysis
    Sham M. Kakade & Dean P. Foster
    In COLT 2007.
    [pdf]

  • Maximum Entropy Correlated Equilibria
    Luis Ortiz, Robert Schapire, & Sham M. Kakade
    In AISTAT 2007.
    [pdf]

  • The Value of Observation for Monitoring Dynamic Systems
    Eyal Even-Dar, Sham M. Kakade, & Yishay Mansour
    In the ICJAI 2007.
    [pdf]

2006

  • Cover Trees for Nearest Neighbor
    Alina Beygelzimer, Sham M. Kakade & John Langford
    In the ICML 2006.
    [pdf]

  • (In)Stability Properties of Limit Order Dynamics.
    E. Even-Dar, S. M. Kakade, M. Kearns, and Y. Mansour.
    In the ACM Conference on Electronic Commerce 2006.
    [ps] [pdf]

  • Calibration via Regression
    Sham M. Kakade & Dean P. Foster
    In the IEEE Information Theory Workshop 2006.
    [pdf]

  • From Batch to Transductive Online Learning
    Sham M. Kakade & Adam Kalai
    In NIPS 2006.
    [pdf]

  • Worst-Case Bounds for Gaussian Process Models
    Sham M. Kakade, Matthias W. Seeger, & Dean P. Foster
    In NIPS 2006.
    [ps] [pdf]

2005

  • Trading in Markovian Price Models
    Sham M. Kakade & Michael Kearns
    In COLT 2005.
    [ps] [pdf]

  • Planning in POMDPs Using Multiplicity Automata
    Eyal Even-Dar, Sham M. Kakade, & Yishay Mansour
    In UAI 2005.
    [ps] [pdf]

  • Reinforcement Learning in POMDPs Without Resets
    Eyal Even-Dar, Sham M. Kakade, & Yishay Mansour
    In IJCAI 2005.
    [ps] [pdf]

  • The Economic Properties of Social Networks.
    Sham M. Kakade, Michael Kearns, Luis Ortiz, Robin Pemantle, & Siddharth Suri.
    In NIPS 2005.
    [ps] [pdf]

  • Experts in a Markov Decision Process
    Eyal Even-Dar, Sham M. Kakade, & Yishay Mansour
    In NIPS 2005.
    [ps] [pdf]

  • Online Bounds for Bayesian Algorithms
    Sham M. Kakade & Andrew Y. Ng
    In NIPS 2005.
    [ps] [pdf]

2004

  • Deterministic Calibration and Nash Equilibrium
    Sham M. Kakade & Dean P. Foster
    In COLT 2004.
    [ps] [pdf]

  • Graphical Economics.
    Sham Kakade, Michael Kearns, & Luis Ortiz.
    In COLT 2004.
    [ps] [pdf]

  • Competitive Algorithms for VWAP and Limit Order Trading.
    Sham Kakade, Michael Kearns, Yishay Mansour, & Luis Ortiz.
    In the Proceedings of the ACM Electronic Commerce Conference 2004.
    [ps] [pdf]

2003

  • Correlated Equilibria in Graphical Games.
    Sham Kakade, Michael Kearns, John Langford, & Luis Ortiz.
    In the Proceedings of the ACM Electronic Commerce Conference 2003.
    [ps] [pdf]
  • Policy Search by Dynamic Programming.
    Drew Bagnell, Sham Kakade, Andrew Ng, & Geoff Schneider.
    In NIPS 2003.
    [ps] [pdf]

  • Exploration in Metric State Spaces.
    Sham Kakade, Michael Kearns, & John Langford.
    In the Proceedings of the 20th International Conference on Machine Learning 2003.
    [ps] [pdf]

2002

  • Approximately Optimal Approximate Reinforcement Learning.
    Sham Kakade & John Langford.
    In Proceedings of the Nineteenth International Conference on Machine Learning 2002.
    [ps] [pdf]

  • Competitive Analysis of the Explore/Exploit Tradeoff.
    John Langford, Martin Zinkevich, & Sham Kakade.
    In Proceedings of the Nineteenth International Conference on Machine Learning 2002.
    [ps] [pdf]

  • A Natural Policy Gradient.
    Sham Kakade.
    In Advances in Neural Information Processing Systems 14 2002.
    [ps] [pdf]

  • An Alternative Objective Function for Markovian Fields.
    Sham Kakade, Yee Whye Teh, & Sam Roweis.
    In Proceedings of the Nineteenth International Conference on Machine Learning 2002.
    [ps]

  • Opponent Interactions Between Serotonin and Dopamine.
    Nathaniel D. Daw, Sham Kakade, & Peter Dayan.
    In Neural Networks 2002.
    [pdf]

  • Dopamine: Generalization and Bonuses
    Sham Kakade & Peter Dayan.
    In Neural Networks 2002.
    [pdf]
    Also see Dopamine Bonuses.
    In Advances in Neural Information Processing Systems 13 2001.
    [ps.gz] [pdf]

  • Acquisition and Extinction in Autoshaping.
    Sham Kakade & Peter Dayan.
    In Psychological Review 2002.
    [ps.gz] [pdf]
    Also see Acquisition in Autoshaping.
    In Advances in Neural Information Processing Systems 12, 2000.
    [ps.gz] [pdf]

2001

  • Optimizing Average Reward Using Discounted Rewards.
    Sham Kakade.
    In Proceedings of the 14th Annual Conference on Computational Learning Theory 2001.
    [ps] [pdf]

  • Explaining Away in Weight Space.
    Peter Dayan & Sham Kakade.
    In Advances in Neural Information Processing Systems 13, 2001.
    [ps.gz] [pdf]

2000

  • Learning and Selective Attention.
    Peter Dayan, Sham Kakade, & P. Read Montague.
    Nature Neuroscience, 3, 1218-1223. 2000.
    [pdf]