Convergence Guarantees for RMSProp and Adam in Generalized-smooth Non-convex Optimization with Affine Noise Variance.
Qi ZhangYi ZhouShaofeng ZouPublished in: CoRR (2024)
Keyphrases
- convex optimization
- noise variance
- operator splitting
- noisy images
- wiener filter
- total variation
- correlation coefficient
- regularization parameter
- gaussian noise
- image restoration
- noise level
- image noise
- convex optimization problems
- convergence rate
- noise reduction
- multiresolution
- spatial domain
- denoising algorithm
- random sampling
- computer vision
- signal to noise ratio
- maximum likelihood
- support vector
- multiscale