NIPS Proceedingsβ

Lihong Li

8 Papers

  • Adversarial Attacks on Stochastic Bandits (2018)
  • Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation (2018)
  • Q-LDA: Uncovering Latent Patterns in Text-based Sequential Decision Processes (2017)
  • Active Learning with Oracle Epiphany (2016)
  • An Empirical Evaluation of Thompson Sampling (2011)
  • Learning from Logged Implicit Exploration Data (2010)
  • Parallelized Stochastic Gradient Descent (2010)
  • Sparse Online Learning via Truncated Gradient (2008)