Plug-In Stochastic Gradient Method
This work addresses scalability issues in signal reconstruction for large datasets, but it is incremental as it builds on existing plug-and-play prior frameworks.
The paper tackles the problem of scaling plug-and-play priors for regularized signal reconstruction to large datasets by introducing an online variant that uses subsets of measurements per iteration, and presents novel convergence results for both batch and online algorithms.
Plug-and-play priors (PnP) is a popular framework for regularized signal reconstruction by using advanced denoisers within an iterative algorithm. In this paper, we discuss our recent online variant of PnP that uses only a subset of measurements at every iteration, which makes it scalable to very large datasets. We additionally present novel convergence results for both batch and online PnP algorithms.