MMSE denoisers correspond to 1-weakly convex regularizers via upper Moreau envelopes of negative log-marginals, enabling the first sublinear convergence rates for PnP proximal gradient descent.
What’s in a prior? learned proximal networks for inverse problems
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
math.OC 2roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Nonasymptotic Convergence Rates for Plug-and-Play Methods With MMSE Denoisers
MMSE denoisers correspond to 1-weakly convex regularizers via upper Moreau envelopes of negative log-marginals, enabling the first sublinear convergence rates for PnP proximal gradient descent.
- Proximal-Based Generative Modeling for Bayesian Inverse Problems