Research map / Learning theory and algorithms / Matrix and tensor methods
Parametric Simplex Method for Sparse Learning
Haotian Pang, Han Liu, Robert J Vanderbei, Tuo Zhao
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 PSM instead of ADMM (flare) for Dantzig selector feasibility | PSM · Dantzig selector path, n=100 d=250 | maximum feasibility violation: 498(122) -> 0(0) | Improved |
| Use PSM instead of ADMM (flare), minimum violation | PSM · Dantzig selector path | minimum feasibility violation: 143(73.2) -> 0(0) | Improved |
| PSM vs flare at d=500 | PSM · Dantzig selector timing | time (s): 19.5(2.72) -> 2.40(0.220) | Improved |
| PSM vs flare at d=1000 | PSM · Dantzig selector timing | time (s): 44.4(2.54) -> 29.7(1.39) | Improved |
| PSM vs flare at d=2000 | PSM · Dantzig selector timing | time (s): 142(11.5) -> 47.5(2.27) | Improved |
| PSM vs flare at d=5000 | PSM · Dantzig selector timing | time (s): 1500(231) -> 649(89.8) | Improved |
| Increase dimension d from 25 to 200 for PSM on differential network | PSM · Differential network | time (s): 0.0185(0.00689) -> 46.88(7.24) | Hurt |
| Increase dimension from 100 to 150 (sparsity level 0.02 to 0.002) | PSM · Differential network | iteration number: 164(58.2) -> 85.8(16.7) | Mixed |
| Run PSM for the Dantzig selector example until nonzeros identified | PSM · Dantzig selector solution path n=100 d=250 | iterations to find all nonzeros: less than 10 iterations | Improved |
| Continue PSM iterations after nonzeros identified | PSM · Dantzig selector solution path | estimation accuracy | No clear effect |
Closest papers by meaning
- Simplex Constrained Sparse Optimization via Tail Screening (JMLR 2025 · similarity 0.86)
- A minimax optimal approach to high-dimensional double sparse linear regression (JMLR 2024 · similarity 0.85)
- Dictionary Learning for Sparse Coding: Algorithms and Convergence Analysis (TPAMI 2016 · similarity 0.84)
- A Feasible Level Proximal Point Method for Nonconvex Sparse Constrained Optimization (NeurIPS 2020 · similarity 0.84)
- Adaptive Forward Stepwise: A Method for High Sparsity Regression (JMLR 2026 · similarity 0.84)
- Iterative Regularization with k-support Norm: An Important Complement to Sparse Recovery (AAAI 2024 · similarity 0.83)
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.
