Quantum Speedups of Optimizing Approximately Convex Functions with Applications to Logarithmic Regret Stochastic Convex Bandits.
Tongyang LiRuizhe ZhangPublished in: CoRR (2022)
Keyphrases
- convex functions
- regret bounds
- lower bound
- online learning
- convex programs
- objective function
- linear regression
- convex programming
- exact penalty
- convex sets
- quasiconvex
- multi armed bandit
- online convex optimization
- dc programming
- linear program
- piecewise linear
- upper bound
- primal dual
- bregman divergences
- variational inequalities
- linear programming
- multi armed bandits
- data points
- special case