Research map / Learning theory and algorithms / Matrix and tensor methods
L0Learn: A Scalable Package for Sparse Learning using L0 Regularization
Hussein Hazimeh, Rahul Mazumder, Tim Nonet
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 L0Learn instead of glmnet | L0Learn · Synthetic linear regression (p=1e5) | prediction error x100: 32.3 -> 9.5 | Improved |
| use L0Learn instead of glmnet | L0Learn · Synthetic linear regression (p=1e5) | time (s): 8.0 -> 4.4 | Improved |
| use L0Learn instead of ncvreg (MCP) | L0Learn · Synthetic linear regression (p=1e5) | time (s): 19.7 -> 4.4 | Improved |
| use L0Learn instead of ncvreg (MCP) | L0Learn · Synthetic linear regression (p=1e3) | time (s): 1.35 -> 0.09 | Improved |
| use L0Learn instead of abess | L0Learn · Synthetic linear regression (p=1e4) | prediction error x100: 16.2 -> 9.4 | Improved |
| use L0Learn instead of abess | L0Learn · Synthetic linear regression (p=1e4) | time (s): 7.21 -> 0.49 | Improved |
| use L0Learn instead of picasso | L0Learn · Synthetic linear regression (p=1e5) | time (s): 15.5 -> 4.4 | Improved |
| use L0Learn instead of glmnet (l1) | L0Learn · Synthetic linear regression (p=1e3) | false positives: 154 -> 0 | Improved |
| use L0Learn instead of glmnet (l1) | L0Learn · Synthetic linear regression (p=1e4) | support size: 350 -> 50 | Improved |
| use MCP penalty (ncvreg) instead of l1 (glmnet) | ncvreg · Synthetic linear regression (p=1e3) | prediction error x100: 19.8 -> 9.4 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- abess — abess: A Fast Best-Subset Selection Library in Python and R (ICML 2023) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Learning Sparse Classifiers: Continuous and Mixed Integer Optimization Perspectives (JMLR 2021 · similarity 0.90)
- Solving L1-regularized SVMs and Related Linear Programs: Revisiting the Effectiveness of Column and Constraint Generation (JMLR 2022 · similarity 0.87)
- Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders (ICML 2026 · similarity 0.87)
- Picasso: A Sparse Learning Library for High Dimensional Data Analysis in R and Python (JMLR 2019 · similarity 0.87)
- Navigating Extremes: Dynamic Sparsity in Large Output Spaces (NeurIPS 2024 · similarity 0.85)
- SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity (ICML 2025 · 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.
