Research map / Learning theory and algorithms / Sample complexity
Exactly Computing the Local Lipschitz Constant of ReLU Networks
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 LP relaxation (LipLP) instead of exact MIP (LipMIP) (ablation) | LipMIP · Binary MNIST (1 vs 7) | runtime (s) and relative error: 69.187 -> 0.226 s; 0.00% -> +39.39% | Mixed |
| use LP relaxation (LipLP) instead of exact MIP (LipMIP) (ablation) | LipMIP · Synthetic dataset | runtime (s) and relative error: 38.844 -> 0.030 s; 0.00% -> +362.43% | Mixed |
Closest papers by meaning
- Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound Propagation (NeurIPS 2022 · similarity 0.94)
- ECLipsE: Efficient Compositional Lipschitz Constant Estimation for Deep Neural Networks (NeurIPS 2024 · similarity 0.91)
- Some Fundamental Aspects about Lipschitz Continuity of Neural Networks (ICLR 2024 · similarity 0.90)
- Approximation theory for 1-Lipschitz ResNets (NeurIPS 2025 · similarity 0.89)
- A provable control of sensitivity of neural networks through a direct parameterization of the overall bi-Lipschitzness (NeurIPS 2024 · similarity 0.88)
- Novel Quadratic Constraints for Extending LipSDP beyond Slope-Restricted Activations (ICLR 2024 · similarity 0.88)
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.