Research map / Learning theory and algorithms / Matrix and tensor methods
Polynomial time algorithms for dual volume sampling
Chengtao Li, Stefanie Jegelka, Suvrit Sra
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 dual volume sampling instead of slower greedy or optimization-based selection | Column selection for experimental design · CompAct(s) | prediction error | No clear effect |
| Use DVS instead of greedy and optimization-based selection | Column selection for experimental design · CompAct(s) | running time | Improved |
| Use optimization- or greedy-based selection instead of sampling-based selection | Experimental-design column selection · CompAct, Abalone, and Bank32NH | prediction error | Mixed |
| Lower the temperature parameter β below 1 (ablation) | DVS generalized sampler · CompAct(s), CompAct, Abalone, and Bank32NH | selection performance | Mixed |
Closest papers by meaning
- Unbiased estimates for linear regression via volume sampling (NeurIPS 2017 · similarity 0.88)
- Provably Correct Algorithms for Matrix Column Subset Selection with Selectively Sampled Data (JMLR 2018 · similarity 0.87)
- Reverse Iterative Volume Sampling for Linear Regression (JMLR 2018 · similarity 0.85)
- Faster Sampling from Log-Concave Densities over Polytopes via Efficient Linear Solvers (ICLR 2024 · similarity 0.84)
- Linear Time Approximation Algorithm for Column Subset Selection with Local Search (NeurIPS 2024 · similarity 0.84)
- Faster Diffusion Sampling with Randomized Midpoints: Sequential and Parallel (ICLR 2025 · 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.
