Achieving Near-Optimal Regret for Bandit Algorithms with Uniform Last-Iterate Guarantee.

Junyan Liu Yunfan Li Lin Yang

Published in: CoRR (2024)

Keyphrases

learning algorithm
orders of magnitude
times faster
data structure
worst case
theoretical analysis
combinatorial optimization
recently developed
upper confidence bound
computational cost
online algorithms
neural network
lower bound
evolutionary algorithm
computationally efficient
regret minimization