KellerJordan / REPAIR
Code release for REPAIR: REnormalizing Permuted Activations for Interpolation Repair
☆47Updated last year
Alternatives and similar repositories for REPAIR:
Users that are interested in REPAIR are comparing it to the libraries listed below
- Git Re-Basin: Merging Models modulo Permutation Symmetries in PyTorch☆75Updated 2 years ago
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆43Updated last year
- ☆23Updated 2 years ago
- Replicating and dissecting the git-re-basin project in one-click-replication Colabs☆36Updated 2 years ago
- Code for the ICLR 2022 paper. Salient Imagenet: How to discover spurious features in deep learning?☆40Updated 2 years ago
- ☆45Updated 2 years ago
- Sharpness-Aware Minimization Leads to Low-Rank Features [NeurIPS 2023]☆28Updated last year
- Source code of "What can linearized neural networks actually say about generalization?☆20Updated 3 years ago
- ☆34Updated last year
- Recycling diverse models☆44Updated 2 years ago
- ☆107Updated last year
- Pytorch code for "Improving Self-Supervised Learning by Characterizing Idealized Representations"☆40Updated 2 years ago
- Towards Understanding Sharpness-Aware Minimization [ICML 2022]☆35Updated 2 years ago
- Training vision models with full-batch gradient descent and regularization☆37Updated 2 years ago
- Model Zoos published at the NeurIPS 2022 Dataset & Benchmark track: "Model Zoos: A Dataset of Diverse Populations of Neural Network Model…☆54Updated last year
- ☆57Updated 2 years ago
- A Continual Learning Library in PyTorch and JAX☆14Updated last year
- Code for the paper "The Journey, Not the Destination: How Data Guides Diffusion Models"☆22Updated last year
- ☆54Updated 4 years ago
- The official PyTorch implementation - Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from t…☆78Updated 2 years ago
- SGD with large step sizes learns sparse features [ICML 2023]☆32Updated last year
- Deep Learning & Information Bottleneck☆59Updated last year
- Code for "The Intrinsic Dimension of Images and Its Impact on Learning" - ICLR 2021 Spotlight https://openreview.net/forum?id=XJk19XzGq2J☆68Updated 11 months ago
- ImageNet Testbed, associated with the paper "Measuring Robustness to Natural Distribution Shifts in Image Classification."☆118Updated last year
- A centralized place for deep thinking code and experiments☆82Updated last year
- Prospect Pruning: Finding Trainable Weights at Initialization Using Meta-Gradients☆31Updated 3 years ago
- ☆27Updated 2 years ago
- Distilling Model Failures as Directions in Latent Space☆46Updated 2 years ago
- Train ImageNet *fast* in 500 lines of code with FFCV☆141Updated 11 months ago
- Rethinking Bias-Variance Trade-off for Generalization of Neural Networks☆49Updated 4 years ago