Quantum Speedups of Optimizing Approximately Convex Functions with Applications to Logarithmic Regret Stochastic Convex Bandits.
Tongyang LiRuizhe ZhangPublished in: NeurIPS (2022)
Keyphrases
- convex functions
- regret bounds
- lower bound
- online learning
- convex programs
- convex programming
- linear regression
- linear program
- exact penalty
- objective function
- multi armed bandit
- quasiconvex
- convex sets
- dc programming
- upper bound
- online convex optimization
- piecewise linear
- primal dual
- worst case
- bregman divergences
- linear programming
- dynamic programming
- multi armed bandits
- np hard
- approximation algorithms
- training samples
- image processing