Lipschitz Bandits: Regret Lower Bound and Optimal Algorithms.

Stefan Magureanu Richard Combes Alexandre Proutière

Published in: COLT (2014)

Keyphrases

lower bound
worst case
regret bounds
multi armed bandit
online algorithms
optimal solution
upper bound

online learning
lower and upper bounds
exhaustive search
learning algorithm
branch and bound
online convex optimization
branch and bound algorithm

objective function
theoretical analysis
average case
expert advice
game theory
loss function
approximation algorithms

learning theory
computationally efficient
upper and lower bounds
optimization problems
competitive ratio
data structure
feature selection