• search
    search
  • reviewers
    reviewers
  • feeds
    feeds
  • assignments
    assignments
  • settings
  • logout

Improved Self-Normalized Concentration in Hilbert Spaces: Sublinear Regret for GP-UCB.

Justin WhitehouseZhiwei Steven WuAaditya Ramdas
Published in: CoRR (2023)
Keyphrases
  • hilbert spaces
  • hilbert space
  • bandit problems
  • multi armed bandit
  • variational inequalities
  • similarity measure
  • pairwise
  • np hard
  • dynamic programming