AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

TFPnP: Tuning-free Plug-and-Play Proximal Algorithms with Applications to Inverse Imaging Problems

Kaixuan Wei, Angelica Aviles-Rivero, Jingwei Liang, Ying Fu, Hua Huang, Carola-Bibiane Schönlieb

JMLR 2022 · Learning theory and algorithms › Matrix and tensor methods · approach: Signal recovery and phase retrieval

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add noise level and step info to policy input (ablation)TFPnP policy · CS-MRI 8x noise 15PSNR / iterations: 26.27 -> 26.52 (iterations 30.0 -> 15.0)Improved
add noise level and step info to policy input (ablation)TFPnP policy · CS-MRI 2x noise 15PSNR / iterations: 30.15 -> 30.33 (iterations 27.4 -> 5.0)Improved
add early-stop penalty eta=0.05 instead of eta=0 (ablation)TFPnP reward · CS-MRI 2x noise 15iterations: 27.1 -> 5.0Improved
raise penalty eta from 0.05 to 0.25 (ablation)TFPnP reward · CS-MRI 8x noise 15PSNR: 26.52 -> 25.53Hurt
vary iterations per step m and horizon N with m x N fixed at 30 (ablation)TFPnP policy · CS-MRI 8x noise 15PSNR: 26.27, 26.39, 26.52No clear effect
optimize pi2 with model-based RL instead of model-free DDPG (ablation)TFPnP policy · CS-MRI Medical7 8x noise 15PSNR: 26.15 -> 26.52Improved
use learned policy instead of oracle fixed parametersPnP-ADMM · CS-MRI Medical7 8x noise 15PSNR: 26.41 -> 26.52Improved
use learned policy instead of handcrafted policyPnP-ADMM · CS-MRI Medical7 8x noise 15PSNR: 25.76 -> 26.52Improved
add optimal early stopping to fixed parametersPnP-ADMM fixed policy · CS-MRI Medical7 2x noise 15PSNR: 23.94 -> 28.45Improved
use U-net instead of DnCNN as denoiser prior (ablation)PnP-ADMM CS-MRI · CS-MRI noise 15PSNR: 25.43 -> 25.76Improved
apply learned policy to PnP-PGMPnP-PGM · CS-MRI 8x noise 15PSNR: 25.85 -> 26.28Improved
apply learned policy to PnP-HQSPnP-HQS · CS-MRI 8x noise 15PSNR: 25.50 -> 25.96Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy