Optimal regret algorithm for Pseudo-1d Bandit Convex Optimization.

Aadirupa Saha Nagarajan Natarajan Praneeth Netrapalli Prateek Jain

Published in: ICML (2021)

Keyphrases

convex optimization
worst case
dynamic programming
optimal solution
learning algorithm
cost function
primal dual
lower bound
objective function
linear programming
denoising
np hard
computational complexity
optimization problems
globally optimal
convex relaxation
upper confidence bound