Research map / Learning theory and algorithms / Matrix and tensor methods
k-Support and Ordered Weighted Sparsity for Overlapping Groups: Hardness and Algorithms
Cong Han Lim, Stephen Wright
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 LG(k) with k equal to the true support size (in groups) instead of latent group lasso (k=1) (ablation) | LG(k) latent k-group support norm · Synthetic overlapping-group linear regression, support recovery | trials with correct support (out of 100) | Improved |
| Use small k (below the true group count) in LG(k) (ablation) | LG(k) · Synthetic overlapping-group linear regression, support recovery | trials with correct support (out of 100) | Mixed |
| Use LGS-OWL with linear or spike weights instead of latent group lasso | LGS-OWL · Synthetic overlapping-group linear regression, support recovery | trials with correct support (out of 100) | Improved |
| Use larger k or LGS-OWL instead of small k (ablation) | LG(k), LGS-OWL · Synthetic overlapping-group linear regression, estimation | RMSE of estimation error | Improved |
| Use l2 variants instead of l-infinity variants of the norms (ablation) | LG(k), LGS-OWL · Synthetic overlapping-group linear regression, support recovery | trials with correct support (out of 100) | Improved |
| Use standard lasso, elastic net, k-support, OWL instead of group-aware norms | Baselines · Synthetic overlapping-group linear regression, support recovery | runs with exact correct support | Hurt |
Closest papers by meaning
- The Non-Overlapping Statistical Approximation to Overlapping Group Lasso (JMLR 2024 · similarity 0.86)
- GAP Safe Screening Rules for Sparse-Group Lasso (NeurIPS 2016 · similarity 0.85)
- Sparse + Group-Sparse Dirty Models: Statistical Guarantees without Unreasonable Conditions and a Case for Non-Convexity (ICML 2017 · similarity 0.85)
- Uncorrelated Group LASSO (AAAI 2016 · similarity 0.85)
- New Perspectives on k-Support and Cluster Norms (JMLR 2016 · similarity 0.85)
- Learning Sparse Group Models Through Boolean Relaxation (ICLR 2023 · 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.
