Research map / Label-efficient and robust learning / Recognition and long-tail
Ensembles of Locally Independent Prediction Models
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 LIT instead of NCL | Ensembles of 256-unit single hidden layer neural networks · Mushroom extrapolation split | AUC: .94±.01 -> .96±.01 | Helped |
| Use LIT instead of Bag | Ensembles of 256-unit single hidden layer neural networks · Ionosphere extrapolation split | AUC: .89±.04 -> .96±.02 | Helped |
| Use LIT instead of Bag | Ensembles of 256-unit single hidden layer neural networks · Sonar extrapolation split | AUC: .82±.03 -> .81±.03 | Hurt |
| Use LIT instead of RRs | Ensembles of 256-unit single hidden layer neural networks · SPECTF extrapolation split | AUC: .83±.05 -> .84±.05 | Helped |
| Use LIT instead of RRs | Ensembles of 256-unit single hidden layer neural networks · Electricity extrapolation split | AUC: .86±.00 -> .87±.00 | Helped |
| Use LIT instead of Ada | Ensembles of 256-unit single hidden layer neural networks · Electricity random split | AUC: .88±.00 -> .87±.00 | Hurt |
| Use LIT instead of NCL | Ensembles of 256-unit single hidden layer neural networks · ICU mortality full dataset (n>10^6) | AUC: .753±.001 -> .750±.001 | Hurt |
| Use LIT instead of NCL | Ensembles of 256-unit single hidden layer neural networks · ICU mortality limited slice (n=10^3) | AUC: .697±.006 -> .711±.001 | Helped |
| Use LIT instead of Bag | Ensembles of 256-unit single hidden layer neural networks · ICU mortality limited slice (n=10^3) | AUC: .690±.002 -> .711±.001 | Helped |
Closest papers by meaning
- Ensemble Pruning for Out-of-distribution Generalization (ICML 2024 · similarity 0.87)
- Sharpness-diversity tradeoff: improving flat ensembles with SharpBalance (NeurIPS 2024 · similarity 0.87)
- Theoretical Limitations of Ensembles in the Age of Overparameterization (ICML 2025 · similarity 0.87)
- No Free Lunch from Random Feature Ensembles: Scaling Laws and Near-Optimality Conditions (ICML 2025 · similarity 0.86)
- Diverse Prototypical Ensembles Improve Robustness to Subpopulation Shift (ICML 2025 · similarity 0.86)
- Conformal Prediction for Ensembles: Improving Efficiency via Score-Based Aggregation (NeurIPS 2025 · similarity 0.86)
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.