Login / Signup

Second Order Regret Bounds Against Generalized Expert Sequences under Partial Bandit Feedback.

Kaan GökcesuHakan Gökcesu
Published in: CoRR (2022)
Keyphrases
  • regret bounds
  • expert advice
  • multi armed bandit
  • lower bound
  • online learning
  • linear regression
  • higher order
  • hidden markov models
  • upper bound
  • active learning
  • least squares
  • e learning
  • optimal solution
  • model selection