JonasGeiping / fullbatchtrainingLinks
Training vision models with full-batch gradient descent and regularization
☆38Updated 2 years ago
Alternatives and similar repositories for fullbatchtraining
Users that are interested in fullbatchtraining are comparing it to the libraries listed below
Sorting:
- ☆55Updated 5 years ago
- Towards Understanding Sharpness-Aware Minimization [ICML 2022]☆35Updated 3 years ago
- Weight-Averaged Sharpness-Aware Minimization (NeurIPS 2022)☆28Updated 2 years ago
- Code for the paper "Understanding Generalization through Visualizations"☆64Updated 4 years ago
- ☆34Updated last year
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆43Updated 2 years ago
- Code for the ICLR 2022 paper. Salient Imagenet: How to discover spurious features in deep learning?☆40Updated 3 years ago
- Computing various measures and generalization bounds on convolutional and fully connected networks☆35Updated 6 years ago
- A Closer Look at Accuracy vs. Robustness☆88Updated 4 years ago
- An Investigation of Why Overparameterization Exacerbates Spurious Correlations☆30Updated 5 years ago
- Simple data balancing baselines for worst-group-accuracy benchmarks.☆42Updated last year
- Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians (ICML 2019)☆16Updated 6 years ago
- ImageNet Testbed, associated with the paper "Measuring Robustness to Natural Distribution Shifts in Image Classification."☆119Updated 2 years ago
- ☆109Updated 2 years ago
- ☆39Updated 2 years ago
- ☆58Updated 2 years ago
- The Pitfalls of Simplicity Bias in Neural Networks [NeurIPS 2020] (http://arxiv.org/abs/2006.07710v2)☆41Updated last year
- Do input gradients highlight discriminative features? [NeurIPS 2021] (https://arxiv.org/abs/2102.12781)☆13Updated 2 years ago
- [ICML'20] Multi Steepest Descent (MSD) for robustness against the union of multiple perturbation models.☆26Updated last year
- Distributional and Outlier Robust Optimization (ICML 2021)☆27Updated 4 years ago
- Code for "Just Train Twice: Improving Group Robustness without Training Group Information"☆72Updated last year
- ☆23Updated 2 years ago
- Distilling Model Failures as Directions in Latent Space☆47Updated 2 years ago
- ☆17Updated 2 years ago
- ICLR 2021, Fair Mixup: Fairness via Interpolation☆57Updated 4 years ago
- Code for "Picking Winning Tickets Before Training by Preserving Gradient Flow" https://openreview.net/pdf?id=SkgsACVKPH☆106Updated 5 years ago
- Gradient Starvation: A Learning Proclivity in Neural Networks☆61Updated 4 years ago
- Code for the CVPR 2021 paper: Understanding Failures of Deep Networks via Robust Feature Extraction☆36Updated 3 years ago
- ☆34Updated 4 years ago
- [ICML 2021] This is the official github repo for training L_inf dist nets with high certified accuracy.☆42Updated 3 years ago