Improved Regret for Bandit Convex Optimization with Delayed Feedback.
Yuanyu WanChang YaoMingli SongLijun ZhangPublished in: CoRR (2024)
Keyphrases
- convex optimization
- delayed feedback
- interior point methods
- online convex optimization
- bandit problems
- low rank
- primal dual
- convex optimization problems
- total variation
- norm minimization
- convex formulation
- convex constraints
- regret bounds
- convex relaxation
- operator splitting
- multi armed bandit
- semi definite programming
- upper confidence bound
- worst case
- lower bound
- multi armed bandit problems
- computer vision
- semidefinite program
- basis pursuit
- image denoising
- online learning
- higher order
- high quality