Research map / Learning theory and algorithms / Prediction and decision losses
Interpretability with full complexity by constraining feature information
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 Distributed IB instead of NODE | Tabular prediction · Bikeshare | RMSE: 36.2 -> 38.0 | Hurt |
| Use Distributed IB instead of NODE | Tabular prediction · Wine | RMSE: 0.64 -> 0.62 | Helped |
| Use Distributed IB instead of NODE-GA²M | Tabular prediction · MIMIC-II | AUC: 84.6 -> 84.9 | Helped |
| Use Distributed IB instead of NODE | Tabular prediction · MIMIC-III | AUC: 82.8 -> 80.2 | Hurt |
| Use Distributed IB instead of NODE | Tabular prediction · Microsoft | MSE: 0.5570 -> 0.5790 | Hurt |
Closest papers by meaning
- Learning to Explain: An Information-Theoretic Perspective on Model Interpretation (ICML 2018 · similarity 0.89)
- Local vs. Global Interpretability: A Computational Complexity Perspective (ICML 2024 · similarity 0.88)
- Explainable Neural Networks with Guarantee: A Sparse Estimation Approach (AAAI 2025 · similarity 0.88)
- What makes an Ensemble (Un) Interpretable? (ICML 2025 · similarity 0.88)
- Enhancing Performance of Explainable AI Models with Constrained Concept Refinement (ICML 2025 · similarity 0.87)
- Sample-efficient Learning of Concepts with Theoretical Guarantees: from Data to Concepts without Interventions (NeurIPS 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.