Research map / Learning theory and algorithms / Matrix and tensor methods
Unique Sharp Local Minimum in L1-minimization Complete Dictionary Learning
Yu Wang, Siqi Wu, Bin Yu
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 |
|---|---|---|---|
| increase perturbation parameter rho beyond 0.35 in the sharpness test (ablation) | Algorithm 1 (perturbation test) · Sharp dictionary, K=20, s=10, n=1600 | distance r: ~10^{-12} -> ~10^{-3} | Hurt |
| use rho between 0.05 and 0.3 in the sharpness test (ablation) | Algorithm 1 (perturbation test) · Sharp vs non-sharp dictionaries, K=20 | distinguishing sharp from non-sharp: around 1.0 (non-sharp) vs ~10^{-12} (sharp) | Improved |
| increase dimension K from 12 to 20 in sharpness identification (ablation) | Algorithm 1 (perturbation test) · Sparse Gaussian s=5, mu=0.5 | sample size for 50% chance: 253, 316, 375 for K = 12, 16, 20 | Hurt |
| use the DL-BCD algorithm with tau=.5 instead of K-SVD, SPAMS, ER-SpUD, EM-BiG-AMP | complete dictionary learning · Recovery rate, n=100K, SNR 100, K=2..20 | recovery rate | Improved |
| replace Gaussian with Laplace coefficients | local identifiability condition · Phase transition, K=10 and 20 | phase transition curve | Improved |
| use reweighting by truncating coefficients above threshold tau (ablation) | DL-BCD · high SNR dictionary learning | numerical performance | Improved |
Closest papers by meaning
- Local Identifiability of $\ell_1$-minimization Dictionary Learning: a Sufficient and Almost Necessary Condition (JMLR 2018 · similarity 0.91)
- Alternating minimization for dictionary learning with random initialization (NeurIPS 2017 · similarity 0.89)
- Global Identifiability of $\ell_1$-based Dictionary Learning via Matrix Volume Optimization (NeurIPS 2023 · similarity 0.89)
- Global Identifiability of Overcomplete Dictionary Learning via L1 and Volume Minimization (ICLR 2025 · similarity 0.88)
- Understanding l4-based Dictionary Learning: Interpretation, Stability, and Robustness (ICLR 2020 · similarity 0.88)
- On the Sparsity-Storage-Accuracy Tradeoff in Parsimoniously Activated Dictionary Learning (NeurIPS 2026 · similarity 0.84)
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.
