AI Paper Atlas

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

Unsupervised Learning From Incomplete Measurements for Inverse Problems

Julián Tachella, Dongdong Chen, Mike Davies

NeurIPS 2022 · Learning theory and algorithms › Matrix and tensor methods · approach: Signal recovery and phase retrieval · 3 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 MOI loss instead of AmbientGANunsupervised inpainting · CelebA inpaintingPSNR (dB): 29.57 -> 34.05Improved
MOI instead of measurement splitting, denoiser architectureunsupervised MRI reconstruction · FastMRI 4xPSNR (dB): 28.72 -> 29.51Improved
MOI instead of measurement splitting, unrolled architectureunsupervised MRI reconstruction · FastMRI 4xPSNR (dB): 29.47 -> 31.39Improved
use unrolled network instead of denoiser network (ablation)MOI · FastMRI 4xPSNR (dB): 29.51 -> 31.39Improved
train measurement splitting on full measurements instead of reduced A_{g,1} (ablation)measurement splitting, denoiser · FastMRI 4xPSNR (dB): 28.72 -> 27.3Hurt
use U-Net instead of DCGAN as AmbientGAN generator (ablation)AmbientGAN · CelebA inpaintingPSNRHurt
fewer measurements/operators than the bound m > k + n/G (ablation)MOI on MNIST · MNIST CS (G=1..40, m=50..400)PSNR improvement over pseudo-inverseHurt

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