tml-epfl / sgd-sparse-featuresLinks
SGD with large step sizes learns sparse features [ICML 2023]
☆33Updated 2 years ago
Alternatives and similar repositories for sgd-sparse-features
Users that are interested in sgd-sparse-features are comparing it to the libraries listed below
Sorting:
- Towards Understanding Sharpness-Aware Minimization [ICML 2022]☆35Updated 3 years ago
- Source code of "What can linearized neural networks actually say about generalization?☆20Updated 3 years ago
- ☆37Updated last year
- Official code for "In Search of Robust Measures of Generalization" (NeurIPS 2020)☆28Updated 4 years ago
- ☆55Updated 5 years ago
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆43Updated last year
- Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians (ICML 2019)☆17Updated 6 years ago
- ☆16Updated 2 years ago
- ☆38Updated 4 years ago
- Training vision models with full-batch gradient descent and regularization☆37Updated 2 years ago
- An Investigation of Why Overparameterization Exacerbates Spurious Correlations☆31Updated 5 years ago
- ☆17Updated last year
- The Pitfalls of Simplicity Bias in Neural Networks [NeurIPS 2020] (http://arxiv.org/abs/2006.07710v2)☆41Updated last year
- ☆59Updated 2 years ago
- Code for the CVPR 2021 paper: Understanding Failures of Deep Networks via Robust Feature Extraction☆36Updated 3 years ago
- Learning perturbation sets for robust machine learning☆65Updated 4 years ago
- ☆62Updated 4 years ago
- A Closer Look at Accuracy vs. Robustness☆88Updated 4 years ago
- Lipschitz Neural Networks described in "Sorting Out Lipschitz Function Approximation" (ICML 2019).☆57Updated 5 years ago
- Source code for "Neural Anisotropy Directions"☆16Updated 4 years ago
- Do input gradients highlight discriminative features? [NeurIPS 2021] (https://arxiv.org/abs/2102.12781)☆13Updated 2 years ago
- Implementations of orthogonal and semi-orthogonal convolutions in the Fourier domain with applications to adversarial robustness☆47Updated 4 years ago
- Implementation of Confidence-Calibrated Adversarial Training (CCAT).☆45Updated 5 years ago
- Geometric Certifications of Neural Nets☆42Updated 2 years ago
- Code for the paper "Understanding Generalization through Visualizations"☆61Updated 4 years ago
- [JMLR] TRADES + random smoothing for certifiable robustness☆14Updated 4 years ago
- ☆34Updated last year
- Distilling Model Failures as Directions in Latent Space☆47Updated 2 years ago
- The Full Spectrum of Deepnet Hessians at Scale: Dynamics with SGD Training and Sample Size☆17Updated 6 years ago
- Computing various measures and generalization bounds on convolutional and fully connected networks☆35Updated 6 years ago