The authors prove that SNORE Prox, a stochastic proximal gradient descent using a denoiser, reaches a stationary point of its objective under nonconvex but weakly convex assumptions.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Convergence Analysis of a Proximal Stochastic Denoising Regularization Algorithm
The authors prove that SNORE Prox, a stochastic proximal gradient descent using a denoiser, reaches a stationary point of its objective under nonconvex but weakly convex assumptions.