AI Chat AI Image Generator AI Video Text to Speech

Plug-In Stochastic Gradient Method

11/08/2018

∙

by Yu Sun, et al.

∙

∙

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.

Yu Sun
127 publications
Brendt Wohlberg
21 publications
Ulugbek S. Kamilov
29 publications

research

∙ 09/12/2018

An Online Plug-and-Play Algorithm for Regularized Image Reconstruction

Plug-and-play priors (PnP) is a powerful framework for regularizing imag...

0 Yu Sun, et al. ∙

research

∙ 10/31/2018

Regularized Fourier Ptychography using an Online Plug-and-Play Algorithm

The plug-and-play priors (PnP) framework has been recently shown to achi...

0 Yu Sun, et al. ∙

research

∙ 11/25/2018

Inexact SARAH Algorithm for Stochastic Optimization

We develop and analyze a variant of variance reducing stochastic gradien...

0 Lam M. Nguyen, et al. ∙

research

∙ 09/04/2023

Corgi^2: A Hybrid Offline-Online Approach To Storage-Aware Data Shuffling For SGD

When using Stochastic Gradient Descent (SGD) for training machine learni...

0 Etay Livne, et al. ∙

research

∙ 06/05/2020

Scalable Plug-and-Play ADMM with Convergence Guarantees

Plug-and-play priors (PnP) is a broadly applicable methodology for solvi...

7 Yu Sun, et al. ∙

research

∙ 09/13/2023

A Flexible Online Framework for Projection-Based STFT Phase Retrieval

Several recent contributions in the field of iterative STFT phase retrie...

0 Tal Peer, et al. ∙

research

∙ 12/11/2012

A Learning Framework for Morphological Operators using Counter-Harmonic Mean

We present a novel framework for learning morphological operators using ...

0 Jonathan Masci, et al. ∙