locuslab / edge-of-stability
☆63Updated 2 months ago
Alternatives and similar repositories for edge-of-stability:
Users that are interested in edge-of-stability are comparing it to the libraries listed below
- Towards Understanding Sharpness-Aware Minimization [ICML 2022]☆35Updated 2 years ago
- Deep Learning & Information Bottleneck☆56Updated last year
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆43Updated last year
- ☆34Updated last year
- [NeurIPS 2021] A Geometric Analysis of Neural Collapse with Unconstrained Features☆55Updated 2 years ago
- Source code of "What can linearized neural networks actually say about generalization?☆20Updated 3 years ago
- Code for the paper: Why Transformers Need Adam: A Hessian Perspective☆49Updated 9 months ago
- Efficient empirical NTKs in PyTorch☆18Updated 2 years ago
- Code for the paper: "Tensor Programs II: Neural Tangent Kernel for Any Architecture"☆104Updated 4 years ago
- Pytorch implementation of KFAC and E-KFAC (Natural Gradient).☆130Updated 5 years ago
- Neural Tangent Kernel Papers☆105Updated last month
- This is an official repository for "LAVA: Data Valuation without Pre-Specified Learning Algorithms" (ICLR2023).☆47Updated 8 months ago
- ☆60Updated 3 years ago
- ☆35Updated 2 years ago
- Simple CIFAR10 ResNet example with JAX.☆23Updated 3 years ago
- Efficient Riemannian Optimization on Stiefel Manifold via Cayley Transform☆37Updated 5 years ago
- Hessian spectral density estimation in TF and Jax☆121Updated 4 years ago
- ☆28Updated last year
- ☆67Updated 5 years ago
- (ICML 2023) Feature learning in deep classifiers through Intermediate Neural Collapse: Accompanying code☆13Updated last year
- Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians (ICML 2019)☆17Updated 5 years ago
- Repository containing Pytorch code for EKFAC and K-FAC perconditioners.☆141Updated last year
- Training vision models with full-batch gradient descent and regularization☆37Updated 2 years ago
- This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…☆35Updated last year
- Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".☆94Updated last year
- [ICML 2021] This is the official github repo for training L_inf dist nets with high certified accuracy.☆41Updated 2 years ago
- An Investigation of Why Overparameterization Exacerbates Spurious Correlations☆30Updated 4 years ago
- PyTorch linear operators for curvature matrices (Hessian, Fisher/GGN, KFAC, ...)☆31Updated this week
- Code for the paper "Pretraining task diversity and the emergence of non-Bayesian in-context learning for regression"☆20Updated last year
- Code release for REPAIR: REnormalizing Permuted Activations for Interpolation Repair☆46Updated last year