Login / Signup
Unimodal Bandits with Continuous Arms: Order-optimal Regret without Smoothness.
Richard Combes
Alexandre Proutière
Alexandre Fauquette
Published in:
Proc. ACM Meas. Anal. Comput. Syst. (2020)
Keyphrases
</>
worst case
objective function
neural network
decision trees
online learning
piecewise linear
operating point
multi armed bandits
machine learning
learning algorithm
optimal solution
pairwise
cost function
prior information
regret bounds
multi armed bandit problems