Research map / Learning theory and algorithms / Matrix and tensor methods
The Constrained Dantzig Selector with Enhanced Consistency
Yinfei Kong, Zemin Zheng, Jinchi Lv
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 flexible constraints (constrained Dantzig selector) instead of Dantzig selector | Dantzig selector · Simulation example 2 (p=1000) | prediction error (x10^-2): 30.8 -> 18.5 | Improved |
| replace simple thresholding with constrained Dantzig selector | thresholded Dantzig selector · Simulation example 2 (p=1000) | prediction error (x10^-2): 28.5 -> 18.5 | Improved |
| compare CDS with adaptive Lasso under high dimensionality | adaptive Lasso · Simulation example 2 (p=10000) | prediction error (x10^-2): 32.4 -> 19.0 | Improved |
| thresholding the Dantzig selector alone | Dantzig selector · Simulation example 2 (p=1000) | prediction error (x10^-2): 30.8 -> 28.5 | Improved |
| increase dimensionality from 1000 to 10000 | Dantzig selector · Simulation example 2 | prediction error (x10^-2): 30.8 -> 54.4 | Hurt |
| increase dimensionality from 1000 to 10000 | constrained Dantzig selector · Simulation example 2 | prediction error (x10^-2): 18.5 -> 19.0 | No clear effect |
| lower lambda from 0.2 to 0.1 (lambda0=0.015) (ablation) | constrained Dantzig selector · Simulation example 2 (p=1000) | prediction error: 0.185 -> 0.196 | Hurt |
| vary lambda0 over 0.001 to 0.03 with lambda>=0.15 (ablation) | constrained Dantzig selector · Simulation example 2 (p=1000) | prediction error: 0.185 (0.001) for lambda 0.2-0.35 | No clear effect |
| use CDS instead of Dantzig selector | Dantzig selector · Real PCR data | prediction error: 0.773 -> 0.660 | Improved |
| use CDS instead of adaptive Lasso | adaptive Lasso · Real PCR data | prediction error: 0.922 -> 0.660 | Improved |
| use CDS instead of Dantzig selector | Dantzig selector · Rat eye gene expression | prediction error: 0.582 -> 0.520 | Improved |
| use CDS instead of elastic net | elastic net · Rat eye gene expression | prediction error: 0.576 -> 0.520 | Improved |
Closest papers by meaning
- Implicit Regularization for Optimal Sparse Recovery (NeurIPS 2019 · similarity 0.86)
- The Price of Sparsity: Sufficient Conditions for Sparse Recovery using Sparse and Sparsified Measurements (NeurIPS 2025 · similarity 0.85)
- Structured Matrix Recovery via the Generalized Dantzig Selector (NeurIPS 2016 · similarity 0.85)
- Sparse Convex Optimization via Adaptively Regularized Hard Thresholding (ICML 2020 · similarity 0.85)
- Exact Recovery of Sparse Binary Vectors from Generalized Linear Measurements (ICML 2025 · similarity 0.85)
- Gradient Compressed Sensing: A Query-Efficient Gradient Estimator for High-Dimensional Zeroth-Order Optimization (ICML 2024 · 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.
