AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Learning to solve TV regularised problems with unrolled algorithms

Hamza Cherkaoui, Jeremias Sulam, Thomas Moreau

NeurIPS 2020 · Optimization › Nonconvex and smooth optimization · approach: Coordinate and Adam convergence analysis · 7 citations (OpenAlex)

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
use analysis formulation instead of synthesis formulation (ablation)unrolled PGD / FISTA for 1D TV · Simulation (n=2000, k=8, m=5), lambda 0.1 and 0.8risk vs iterationsImproved
learn parameters of unrolled PGD with prox-TV (LPGD-Taut, LPGD-LISTA) vs iterative PGDanalysis PGD · Simulation, low iteration regimerisk vs iterationsImproved
high regularization (lambda 0.8) vs low (0.1) for LPGD-LISTALPGD-LISTA with 50 inner layers · Simulationrisk vs iterationsHurt
high regularization (lambda 0.8) vs low (0.1) for LPGD-TautLPGD-Taut · Simulationrisk vs iterationsHurt
train the inner LISTA parameters of unrolled prox-TV vs untrained initialization (ablation)LPGD-LISTA · Simulation, prox-TV error, T in [20,50]prox-TV errorNo clear effect
LPGD-Taut vs Accelerated PGD (analysis)fMRI deconvolution, UK Biobank · fMRI data, lambda 0.1risk vs iterationsImproved
raise lambda from 0.1 to 0.8 lambda_maxLPGD-Taut · fMRI dataacceleration over PGDHurt

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