NIPS Proceedingsβ

Daniel J. Hsu

21 Papers

  • Benefits of over-parameterization with EM (2018)
  • Leveraged volume sampling for linear regression (2018)
  • Overfitting or perfect fitting? Risk bounds for classification and regression rules that interpolate (2018)
  • Linear regression without correspondence (2017)
  • Global Analysis of Expectation Maximization for Mixtures of Two Gaussians (2016)
  • Search Improves Label for Active Learning (2016)
  • Efficient and Parsimonious Agnostic Active Learning (2015)
  • Mixing Time Estimation in Reversible Markov Chains from a Single Sample Path (2015)
  • Scalable Non-linear Learning with Adaptive Polynomial Expansions (2014)
  • The Large Margin Mechanism for Differentially Private Maximization (2014)
  • Contrastive Learning Using Spectral Methods (2013)
  • 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)
  • Spectral Methods for Learning Multivariate Latent Tree Structure (2011)
  • Stochastic convex optimization with bandit feedback (2011)
  • Agnostic Active Learning Without Constraints (2010)
  • A Parameter-free Hedging Algorithm (2009)
  • Multi-Label Prediction via Compressed Sensing (2009)
  • A general agnostic active learning algorithm (2007)