NIPS Proceedingsβ

Ambuj Tewari

23 Papers

  • Active Learning for Non-Parametric Regression Using Purely Random Trees (2018)
  • But How Does It Work in Theory? Linear SVM with Random Features (2018)
  • Action Centered Contextual Bandits (2017)
  • Online multiclass boosting (2017)
  • Phased Exploration with Greedy Exploitation in Stochastic Combinatorial Partial Monitoring Games (2016)
  • Alternating Minimization for Regression Problems with Vector-valued Outputs (2015)
  • Fighting Bandits with a New Kind of Smoothness (2015)
  • Predtron: A Family of Online Algorithms for General Prediction Problems (2015)
  • On Iterative Hard Thresholding Methods for High-dimensional M-Estimation (2014)
  • Convex Calibrated Surrogates for Low-Rank Loss Matrices with Applications to Subset Ranking Losses (2013)
  • Learning with Noisy Labels (2013)
  • Feature Clustering for Accelerating Parallel Coordinate Descent (2012)
  • Greedy Algorithms for Structurally Constrained High Dimensional Problems (2011)
  • Nearest Neighbor based Greedy Coordinate Descent (2011)
  • Online Learning: Stochastic, Constrained, and Smoothed Adversaries (2011)
  • On the Universality of Online Mirror Descent (2011)
  • Orthogonal Matching Pursuit with Replacement (2011)
  • Online Learning: Random Averages, Combinatorial Parameters, and Learnability (2010)
  • Smoothness, Low Noise and Fast Rates (2010)
  • On the Complexity of Linear Prediction: Risk Bounds, Margin Bounds, and Regularization (2008)
  • On the Generalization Ability of Online Strongly Convex Programming Algorithms (2008)
  • Optimistic Linear Programming gives Logarithmic Regret for Irreducible MDPs (2007)
  • Sample Complexity of Policy Search with Known Dynamics (2006)