Best-of-Three-Worlds Linear Bandit Algorithm with Variance-Adaptive Regret Bounds.

Shinji Ito Kei Takemura

Published in: COLT (2023)

Keyphrases

regret bounds
learning algorithm
optimal solution
worst case
objective function
computational complexity
k means
probabilistic model
parameter estimation
lower bound
support vector machine
online learning
expectation maximization
information theoretic
prediction error