AI Paper Atlas

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

Non-Convex Rank/Sparsity Regularization and Local Minima

Carl Olsson, Marcus Carlsson, Fredrik Andersson, Viktor Larsson

ICCV 2017 · Learning theory and algorithms › Matrix and tensor methods · approach: Low-rank approximation theory · 18 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 non-convex r_mu regularizer instead of nuclear normlow rank recovery (20x20, rank 5) · synthetic, 202x202 A, delta=0.2distance to ground truthImproved
use non-convex r_mu regularizer instead of nuclear normlow rank recovery, under-determined 300x202 A · synthetic, unknown deltadistance to ground truthImproved
increase noise level with nuclear normnuclear norm relaxation · synthetic low rank recoveryshrinking biasHurt
use r_mu instead of nuclear norm for data fitnon-rigid reconstruction · MOCAP Drink, Pick-up, Stretch, Yogadata fit versus rankImproved
use r_mu instead of nuclear norm at higher ranksnon-rigid reconstruction · MOCAP sequences, rank above about 3-4distance to ground truthHurt
add derivative prior on 3D trajectories with r_mu (ablation)non-rigid reconstruction · MOCAP sequencesdata fit and distance to ground truthMixed

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