Research map / Optimization / Distributed and compressed
DICOD: Distributed Convolutional Coordinate Descent for Convolutional 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 |
|---|---|---|---|
| Locally greedy updates (LGCD) instead of full greedy selection | sequential coordinate descent · Synthetic long signal | iterations and runtime to convergence | Helped |
| Distributing greedy CD across cores with local communication (DICOD) | greedy coordinate descent for convolutional sparse coding · Synthetic long signal | runtime | Helped |
| Increasing number of cores beyond the sweet spot (M*alpha approaching 1/2) | DICOD · Speedup evaluation T=150W and T=750W | speedup | Hurt |
| Randomized coordinate descent instead of greedy selection | coordinate descent · Synthetic long signal | iterations to convergence | Hurt |
| Using a larger number of segments M (interference-prone) in LGCD vs DICOD30 with more cores | DICOD · Synthetic long signal, iterations | iterations to reach accuracy | Hurt |
Closest papers by meaning
- Online Convolutional Sparse Coding with Sample-Dependent Dictionary (ICML 2018 · similarity 0.87)
- A Local Block Coordinate Descent Algorithm for the CSC Model (CVPR 2019 · similarity 0.87)
- A Provable Approach for Double-Sparse Coding (AAAI 2018 · similarity 0.86)
- A General Efficient Hyperparameter-Free Algorithm for Convolutional Sparse Learning (AAAI 2017 · similarity 0.86)
- A Data-Driven and Distributed Approach to Sparse Signal Representation and Recovery (ICLR 2019 · similarity 0.86)
- Accelerating Sparse Convolution with Column Vector-Wise Sparsity (NeurIPS 2022 · similarity 0.85)
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.