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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use non-convex r_mu regularizer instead of nuclear norm | low rank recovery (20x20, rank 5) · synthetic, 202x202 A, delta=0.2 | distance to ground truth | Improved |
| use non-convex r_mu regularizer instead of nuclear norm | low rank recovery, under-determined 300x202 A · synthetic, unknown delta | distance to ground truth | Improved |
| increase noise level with nuclear norm | nuclear norm relaxation · synthetic low rank recovery | shrinking bias | Hurt |
| use r_mu instead of nuclear norm for data fit | non-rigid reconstruction · MOCAP Drink, Pick-up, Stretch, Yoga | data fit versus rank | Improved |
| use r_mu instead of nuclear norm at higher ranks | non-rigid reconstruction · MOCAP sequences, rank above about 3-4 | distance to ground truth | Hurt |
| add derivative prior on 3D trajectories with r_mu (ablation) | non-rigid reconstruction · MOCAP sequences | data fit and distance to ground truth | Mixed |
Closest papers by meaning
- How Much Restricted Isometry is Needed In Nonconvex Matrix Recovery? (NeurIPS 2018 · similarity 0.92)
- Sharp Restricted Isometry Property Bounds for Low-Rank Matrix Recovery Problems with Corrupted Measurements (AAAI 2022 · similarity 0.89)
- A novel variational form of the Schatten-$p$ quasi-norm (NeurIPS 2020 · similarity 0.89)
- Sharp Restricted Isometry Bounds for the Inexistence of Spurious Local Minima in Nonconvex Matrix Recovery (JMLR 2019 · similarity 0.89)
- Affine Rank Minimization via Asymptotic Log-Det Iteratively Reweighted Least Squares (JMLR 2025 · similarity 0.88)
- Factor Group-Sparse Regularization for Efficient Low-Rank Matrix Recovery (NeurIPS 2019 · similarity 0.87)
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.
