Research map / Learning theory and algorithms / Kernels and regression theory
Certifying the True Error: Machine Learning in Coq with Verified Generalization Guarantees
Alexander Bagnall, Gordon Stewart
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 |
|---|---|---|---|
| quantize weights to 2 bits instead of 16 bits (ablation) | 10-ReLU network · EMNIST Digits, union bound | certified accuracy bound: 53% -> 77% | Improved |
| quantize weights to 2 bits instead of 16 bits (ablation) | 10-ReLU network · EMNIST Digits | test accuracy: 0.957 -> 0.926 | Hurt |
| quantize weights to 2 bits instead of 16 bits (ablation) | 10-ReLU network · EMNIST Digits, holdout bound | certified accuracy bound: 94% -> 91% | Hurt |
| use holdout test set instead of union bound on training data | MLCert · EMNIST Digits, 2-bit net | certified accuracy bound: 77% -> 91% | Improved |
Closest papers by meaning
- Certification-Enhanced Generalization Bounds (NeurIPS 2026 · similarity 0.88)
- Slower Generalization, Faster Memorization: A Sweet Spot in Algorithmic Learning (NeurIPS 2026 · similarity 0.85)
- Fantastic Generalization Measures are Nowhere to be Found (ICLR 2024 · similarity 0.85)
- Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel (NeurIPS 2025 · similarity 0.84)
- Generalizability of Neural Networks Minimizing Empirical Risk Based on Expressive Power (ICLR 2025 · similarity 0.84)
- Tighter CMI-Based Generalization Bounds via Stochastic Projection and Quantization (NeurIPS 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.
