Research map / Learning theory and algorithms / Prediction and decision losses
Leveraging Importance Weights in Subset Selection
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 |
|---|---|---|---|
| IWeS-dis importance-weighted sampling versus margin sampling, BADGE, Coreset and random sampling | IWeS-dis · six multi-class image datasets, VGG16 | test accuracy | Helped |
| use IWeS-dis (two models, label information) instead of IWeS-ent (entropy) (ablation) | IWeS · multi-class datasets, VGG16 | test accuracy | Helped |
| IWeS-ent without label information versus baselines | IWeS-ent · multi-class datasets, VGG16 | test accuracy | Helped |
| IWeS-ent versus baselines at larger numbers of selected examples | IWeS-ent · Open Images v6, ResNet101 | Pooled AP | Helped |
| BADGE versus uncertainty sampling with fewer than 800K selected examples | BADGE · Open Images v6 | Pooled AP | Mixed |
| Coreset versus random sampling | Coreset · Open Images v6 and multi-class datasets | accuracy / Pooled AP | No clear effect |
Closest papers by meaning
- Most Influential Subset Selection: Challenges, Promises, and Beyond (NeurIPS 2024 · similarity 0.87)
- Balancing Feature Similarity and Label Variability for Optimal Size-Aware One-shot Subset Selection (ICML 2024 · similarity 0.86)
- Towards a statistical theory of data selection under weak supervision (ICLR 2024 · similarity 0.86)
- Diversified Batch Selection for Training Acceleration (ICML 2024 · similarity 0.86)
- Optimizing importance weighting in the presence of sub-population shifts (ICLR 2025 · similarity 0.86)
- Structural-Entropy-Based Sample Selection for Efficient and Effective Learning (ICLR 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.