Research map / Optimization / Nonconvex and smooth optimization
Complexity of Block Coordinate Descent with Proximal Regularization and Applications to Wasserstein CP-dictionary Learning
Dohyun Kwon, Hanbaek Lyu
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 |
|---|---|---|---|
| Add proximal regularization with a suitable coefficient | WCPDL · Wasserstein CP-dictionary learning | relative reconstruction error vs. time | Improved |
| Set the proximal regularization coefficient to zero instead of using a suitable positive coefficient (ablation) | WCPDL · Wasserstein CP-dictionary learning | relative reconstruction error vs. time | Hurt |
| Use an entropic Wasserstein objective for distribution-valued dictionary learning | Wasserstein dictionary learning · Wasserstein barycenter problem | geometric representation of distributions | Improved |
| Vary the entropic regularization parameter \gamma (ablation) | Wasserstein barycenter · Two \sqcup-shaped distributions | shape of the barycenter distribution: \gamma = 0.002; \gamma = 0.005 | Mixed |
Closest papers by meaning
- On Faster Convergence of Cyclic Block Coordinate Descent-type Methods for Strongly Convex Minimization (JMLR 2018 · similarity 0.88)
- Alternating Randomized Block Coordinate Descent (ICML 2018 · similarity 0.87)
- Unique Sharp Local Minimum in L1-minimization Complete Dictionary Learning (JMLR 2020 · similarity 0.87)
- Block Coordinate Descent for Neural Networks Provably Finds Global Minima (NeurIPS 2025 · similarity 0.86)
- Mirror and Preconditioned Gradient Descent in Wasserstein Space (NeurIPS 2024 · similarity 0.85)
- Smoothing Proximal Gradient Methods for Nonsmooth Sparsity Constrained Optimization: Optimality Conditions and Global Convergence (ICML 2024 · 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.
