Research map / Learning theory and algorithms / Sample complexity
Data-dependent Sample Complexity of Deep Neural Networks via Lipschitz Augmentation
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 |
|---|---|---|---|
| Add Jacobian regularization (ablation) | WideResNet16 with BatchNorm · CIFAR10, low learning rate (0.01) | test error: 5.98% -> 5.46% | Helped |
| Add Jacobian regularization (ablation) | WideResNet16 with BatchNorm · CIFAR10, no data augmentation | test error: 10.44% -> 8.25% | Helped |
| Add Jacobian regularization (ablation) | WideResNet16 with LayerNorm · CIFAR10, no BatchNorm | test error: 6.20% -> 5.57% | Helped |
| Replace BatchNorm with LayerNorm (ablation) | WideResNet16 without Jacobian regularization · CIFAR10, no BatchNorm | test error: 6.65% -> 6.20% | Helped |
Closest papers by meaning
- Width Independent Bounds for the Local Lipschitz Constant of Deep Neural Networks at Random Initialization and after Lazy Training (ICML 2026 · similarity 0.91)
- On Measuring Excess Capacity in Neural Networks (NeurIPS 2022 · similarity 0.90)
- Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks (NeurIPS 2019 · similarity 0.90)
- ECLipsE: Efficient Compositional Lipschitz Constant Estimation for Deep Neural Networks (NeurIPS 2024 · similarity 0.89)
- Why High-rank Neural Networks Generalize?: An Algebraic Framework with RKHSs (ICLR 2026 · similarity 0.89)
- Sharper Guarantees for Learning Neural Network Classifiers with Gradient Methods (ICLR 2025 · similarity 0.89)
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.