tml-epfl / understanding-sam
Towards Understanding Sharpness-Aware Minimization [ICML 2022]
☆35Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for understanding-sam
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆42Updated last year
- ☆32Updated 9 months ago
- Source code of "What can linearized neural networks actually say about generalization?☆18Updated 3 years ago
- Training vision models with full-batch gradient descent and regularization☆38Updated last year
- ☆55Updated 4 years ago
- Official code for "In Search of Robust Measures of Generalization" (NeurIPS 2020)☆28Updated 3 years ago
- ☆58Updated last year
- The Pitfalls of Simplicity Bias in Neural Networks [NeurIPS 2020] (http://arxiv.org/abs/2006.07710v2)☆39Updated 9 months ago
- Simple data balancing baselines for worst-group-accuracy benchmarks.☆40Updated last year
- [NeurIPS 2021] A Geometric Analysis of Neural Collapse with Unconstrained Features☆53Updated 2 years ago
- Distilling Model Failures as Directions in Latent Space☆45Updated last year
- Code for "Just Train Twice: Improving Group Robustness without Training Group Information"☆66Updated 5 months ago
- Code release for REPAIR: REnormalizing Permuted Activations for Interpolation Repair☆45Updated 9 months ago
- Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians (ICML 2019)☆17Updated 5 years ago
- On the effectiveness of adversarial training against common corruptions [UAI 2022]☆30Updated 2 years ago
- Code for the paper "Understanding Generalization through Visualizations"☆60Updated 3 years ago
- Sharpness-Aware Minimization Leads to Low-Rank Features [NeurIPS 2023]☆25Updated last year
- On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them [NeurIPS 2020]☆35Updated 3 years ago
- Weight-Averaged Sharpness-Aware Minimization (NeurIPS 2022)☆26Updated last year
- [ICLR'22] Self-supervised learning optimally robust representations for domain shift.☆23Updated 2 years ago
- Implementation of Confidence-Calibrated Adversarial Training (CCAT).☆45Updated 4 years ago
- Code for the paper "MMA Training: Direct Input Space Margin Maximization through Adversarial Training"☆34Updated 4 years ago
- Pytorch code for "Improving Self-Supervised Learning by Characterizing Idealized Representations"☆40Updated last year
- This is an official repository for "LAVA: Data Valuation without Pre-Specified Learning Algorithms" (ICLR2023).☆44Updated 5 months ago
- Simple CIFAR10 ResNet example with JAX.☆21Updated 3 years ago
- Gradient Starvation: A Learning Proclivity in Neural Networks☆60Updated 3 years ago
- ☆41Updated last year
- Do input gradients highlight discriminative features? [NeurIPS 2021] (https://arxiv.org/abs/2102.12781)☆13Updated last year
- Code relative to "Adversarial robustness against multiple and single $l_p$-threat models via quick fine-tuning of robust classifiers"☆15Updated last year