Login / Signup
Unimodal Bandits: Regret Lower Bounds and Optimal Algorithms.
Richard Combes
Alexandre Proutière
Published in:
CoRR (2014)
Keyphrases
</>
lower bound
regret bounds
worst case
upper bound
online algorithms
multi armed bandit
computational complexity
np hard
computationally efficient
learning algorithm
dynamic programming
theoretical analysis
upper and lower bounds
optimal solution
linear regression
constant factor