Research map / Learning theory and algorithms / Matrix and tensor methods
NOODL: Provable Online Dictionary Learning and Sparse Coding
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 IHT-based coefficient updates instead of a simple hard-thresholding coefficient estimate | Online dictionary learning · Synthetic dictionary learning | dictionary estimation bias | Helped |
| Use IHT-based coefficient updates rather than the biased Arora15 procedure | NOODL · Synthetic dictionary learning | dictionary recovery | Helped |
| Use NOODL rather than Arora15 (unbiased) | Online dictionary learning · Synthetic dictionary learning | dictionary recovery | Helped |
| Use NOODL rather than Mairal 09 | Online dictionary learning · Synthetic dictionary learning | convergence speed | Helped |
| Increase sparsity to k=100 | NOODL · Synthetic dictionary learning | convergence | Helped |
| Use IHT-based coefficient updates to remove dependence on the initial coefficient estimate | NOODL · Synthetic dictionary learning | sample complexity: \tilde{\Omega}(mk) -> \tilde{\Omega}(mk^2) | Hurt |
Closest papers by meaning
- Alternating minimization for dictionary learning with random initialization (NeurIPS 2017 · similarity 0.90)
- Subgradient Descent Learns Orthogonal Dictionaries (ICLR 2019 · 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 0.85)
- Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning (NeurIPS 2024 · similarity 0.85)
- Efficient Dictionary Learning with Switch Sparse Autoencoders (ICLR 2025 · 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.