Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex Optimization.
Zhenxun ZhuangAshok CutkoskyFrancesco OrabonaPublished in: CoRR (2019)
Keyphrases
- convex optimization
- online learning
- regret bounds
- online convex optimization
- interior point methods
- convex relaxation
- total variation
- e learning
- approximate dynamic programming
- low rank
- primal dual
- augmented lagrangian
- semidefinite program
- norm minimization
- active learning
- convex optimization problems
- operator splitting
- convex formulation
- image denoising
- semi definite programming
- computer vision
- image processing
- denoising
- np hard
- low rank matrix
- convex constraints
- image restoration
- linear combination