Research map / Learning theory and algorithms / Kernels and regression theory
On Leave-One-Out Conditional Mutual Information For Generalization
Mohamad Rida Rammal, Alessandro Achille, Aditya Golatkar, Suhas Diggavi, Stefano Soatto
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 f-CMI (prediction-based) bound instead of loo-CMI (weight-based) bound (ablation) | CMI generalization bound · MIT-67 | generalization bound: 9.65 -> 0.493 | Improved |
| Use f-CMI bound instead of loo-CMI bound (ablation) | CMI generalization bound · Oxford Pets | generalization bound: 8.51 -> 0.514 | Improved |
| Increase training set size (fraction of dataset) | f-CMI bound · MIT-67 and Oxford Pets | generalization bound | Improved |
| Increase noise std sigma | f-CMI bound · image classification | generalization bound | Improved |
| Increase noise std sigma | noised model h_sigma · image classification | test error | Hurt |
Closest papers by meaning
- A New Family of Generalization Bounds Using Samplewise Evaluated CMI (NeurIPS 2022 · similarity 0.92)
- Tighter CMI-Based Generalization Bounds via Stochastic Projection and Quantization (NeurIPS 2025 · similarity 0.91)
- Towards Generalization beyond Pointwise Learning: A Unified Information-theoretic Perspective (ICML 2024 · similarity 0.89)
- Exactly Tight Information-theoretic Generalization Bounds via Binary Jensen-Shannon Divergence (ICML 2025 · similarity 0.88)
- Slicing Mutual Information Generalization Bounds for Neural Networks (ICML 2024 · similarity 0.88)
- Fantastic Generalization Measures are Nowhere to be Found (ICLR 2024 · 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.
