NIPS Proceedingsβ

Peter L. Bartlett

19 Papers

  • Information-theoretic lower bounds on the oracle complexity of convex optimization (2009)
  • Adaptive Online Gradient Descent (2007)
  • Optimistic Linear Programming gives Logarithmic Regret for Irreducible MDPs (2007)
  • AdaBoost is Consistent (2006)
  • Sample Complexity of Policy Search with Known Dynamics (2006)
  • Shifting, One-Inclusion Mistake Bounds and Tight Multiclass Expected Risk Bounds (2006)
  • Exponentiated Gradient Algorithms for Large-margin Structured Classification (2004)
  • Large Margin Classifiers: Convex Loss, Low Noise, and Convergence Rates (2003)
  • Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning (2001)
  • Sparse Greedy Gaussian Process Regression (2000)
  • Boosting Algorithms as Gradient Descent (1999)
  • Almost Linear VC Dimension Bounds for Piecewise Polynomial Networks (1998)
  • Direct Optimization of Margins Improves Generalization in Combined Classifiers (1998)
  • Shrinking the Tube: A New Support Vector Regression Algorithm (1998)
  • Generalization in Decision Trees and DNF: Does Size Matter? (1997)
  • The Canonical Distortion Measure in Feature Space and 1-NN Classification (1997)
  • For Valid Generalization the Size of the Weights is More Important than the Size of the Network (1996)
  • Examples of learning curves from a modified VC-formalism (1995)
  • Splines, Rational Functions and Neural Networks (1991)

    • 1 Book

  • Advances in Neural Information Processing Systems 24 (2011)