AnonymousNIPS2019 / DeepnetHessianLinks
The Full Spectrum of Deepnet Hessians at Scale: Dynamics with SGD Training and Sample Size
☆17Updated 6 years ago
Alternatives and similar repositories for DeepnetHessian
Users that are interested in DeepnetHessian are comparing it to the libraries listed below
Sorting:
- Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians (ICML 2019)☆17Updated 6 years ago
- ☆55Updated 4 years ago
- Public code for a paper "Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks."☆34Updated 6 years ago
- Provable Robustness of ReLU networks via Maximization of Linear Regions [AISTATS 2019]☆32Updated 4 years ago
- Distributional and Outlier Robust Optimization (ICML 2021)☆27Updated 3 years ago
- Code for the paper "Understanding Generalization through Visualizations"☆60Updated 4 years ago
- Towards Understanding Sharpness-Aware Minimization [ICML 2022]☆35Updated 2 years ago
- Geometric Certifications of Neural Nets☆41Updated 2 years ago
- The Pitfalls of Simplicity Bias in Neural Networks [NeurIPS 2020] (http://arxiv.org/abs/2006.07710v2)☆40Updated last year
- ☆58Updated 2 years ago
- Simple data balancing baselines for worst-group-accuracy benchmarks.☆42Updated last year
- ☆38Updated 3 years ago
- An Investigation of Why Overparameterization Exacerbates Spurious Correlations☆31Updated 4 years ago
- Implementation of Methods Proposed in Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks (NeurIPS 2019)☆35Updated 4 years ago
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆43Updated last year
- ☆34Updated 4 years ago
- Gradient Starvation: A Learning Proclivity in Neural Networks☆61Updated 4 years ago
- ☆34Updated 3 years ago
- ☆62Updated 3 years ago
- [ICML'20] Multi Steepest Descent (MSD) for robustness against the union of multiple perturbation models.☆26Updated 10 months ago
- ☆20Updated 4 years ago
- Implementation of Information Dropout☆39Updated 7 years ago
- Implementation of Confidence-Calibrated Adversarial Training (CCAT).☆45Updated 4 years ago
- CIFAR-5m dataset☆39Updated 4 years ago
- Randomized Smoothing of All Shapes and Sizes (ICML 2020).☆52Updated 4 years ago
- ☆87Updated 10 months ago
- [JMLR] TRADES + random smoothing for certifiable robustness☆14Updated 4 years ago
- Official code for "In Search of Robust Measures of Generalization" (NeurIPS 2020)☆28Updated 4 years ago
- Official implementation for Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds (NeurIPS, 2021).☆23Updated 2 years ago
- Computing various norms/measures on over-parametrized neural networks☆49Updated 6 years ago