NIPS Proceedingsβ

Sham M. Kakade

23 Papers

  • Learning Overcomplete HMMs (2017)
  • Towards Generalization and Simplicity in Continuous Control (2017)
  • Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent (2016)
  • Convergence Rates of Active Learning for Maximum Likelihood Estimation (2015)
  • Super-Resolution Off the Grid (2015)
  • When are Overcomplete Topic Models Identifiable? Uniqueness of Tensor Tucker Decompositions with Structured Sparsity (2013)
  • A Spectral Algorithm for Latent Dirichlet Allocation (2012)
  • Identifiability and Unmixing of Latent Parse Trees (2012)
  • Learning Mixtures of Tree Graphical Models (2012)
  • Efficient Learning of Generalized Linear and Single Index Models with Isotonic Regression (2011)
  • Spectral Methods for Learning Multivariate Latent Tree Structure (2011)
  • Stochastic convex optimization with bandit feedback (2011)
  • Learning from Logged Implicit Exploration Data (2010)
  • Multi-Label Prediction via Compressed Sensing (2009)
  • Mind the Duality Gap: Logarithmic regret algorithms for online optimization (2008)
  • On the Complexity of Linear Prediction: Risk Bounds, Margin Bounds, and Regularization (2008)
  • On the Generalization Ability of Online Strongly Convex Programming Algorithms (2008)
  • The Price of Bandit Information for Online Optimization (2007)
  • Economic Properties of Social Networks (2004)
  • Experts in a Markov Decision Process (2004)
  • Online Bounds for Bayesian Algorithms (2004)
  • Policy Search by Dynamic Programming (2003)
  • A Natural Policy Gradient (2001)