Research map / Learning theory and algorithms / Sample complexity
Optimal Subsampling with Influence Functions
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 influence-based sampling instead of uniform sampling | Linear least squares and quantile regression · CASP | sample size at matched error | Helped |
| Use influence-based sampling instead of uniform sampling | Linear least squares · Online News Popularity | fit quality | Helped |
| Use residual-only sampling instead of gradient-based sampling (ablation) | Linear regression · CASP | fit quality | Helped |
| Use approximate leverage-based sampling instead of uniform sampling (ablation) | Linear regression · CASP prediction error | prediction error | Helped |
| Use approximate leverage-based sampling instead of uniform sampling (ablation) | Linear regression · CASP coefficient estimation | coefficient error | Hurt |
| Use exact leverage scores instead of influence-based sampling (ablation) | Linear regression and quantile regression · CASP | fit quality | Hurt |
| Use residual-only sampling instead of approximating the regression-design influence (ablation) | Linear least squares · Online News Popularity | fit quality | Helped |
| Use influence sampling customized for the prediction target rather than parameter estimation (ablation) | Linear regression · CASP prediction error | prediction error | Helped |
Closest papers by meaning
- Scale-invariant Optimal Sampling for Rare-events Data and Sparse Models (NeurIPS 2024 · similarity 0.88)
- Towards a statistical theory of data selection under weak supervision (ICLR 2024 · similarity 0.87)
- Most Influential Subset Selection: Challenges, Promises, and Beyond (NeurIPS 2024 · similarity 0.85)
- Robust Sampling for Active Statistical Inference (NeurIPS 2025 · similarity 0.85)
- Minimax Optimality of Score-based Diffusion Models: Beyond the Density Lower Bound Assumptions (ICML 2024 · similarity 0.84)
- Influence Functions for Scalable Data Attribution in Diffusion Models (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.