google-deepmind / sam_edge
☆17Updated 2 months ago
Alternatives and similar repositories for sam_edge:
Users that are interested in sam_edge are comparing it to the libraries listed below
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆43Updated last year
- ☆18Updated 11 months ago
- Replicating and dissecting the git-re-basin project in one-click-replication Colabs☆36Updated 2 years ago
- ☆58Updated 3 years ago
- Parameter-Free Optimizers for Pytorch☆109Updated 8 months ago
- ☆62Updated last month
- Computationally friendly hyper-parameter search with DP-SGD☆23Updated last week
- Distilling Model Failures as Directions in Latent Space☆46Updated last year
- Code accompanying our paper "Feature Learning in Infinite-Width Neural Networks" (https://arxiv.org/abs/2011.14522)☆58Updated 3 years ago
- ☆27Updated last year
- Code for the paper "Pretraining task diversity and the emergence of non-Bayesian in-context learning for regression"☆20Updated last year
- Quantification of Uncertainty with Adversarial Models☆27Updated last year
- Pytorch Datasets for Easy-To-Hard☆26Updated last week
- Omnigrok: Grokking Beyond Algorithmic Data☆51Updated last year
- ☆20Updated 3 months ago
- Code release for REPAIR: REnormalizing Permuted Activations for Interpolation Repair☆46Updated 11 months ago
- Hessian spectral density estimation in TF and Jax☆120Updated 4 years ago
- Pre-trained Gaussian processes for Bayesian optimization☆88Updated last month
- Towards Understanding Sharpness-Aware Minimization [ICML 2022]☆35Updated 2 years ago
- DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule☆58Updated last year
- ☆34Updated 11 months ago
- This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…☆34Updated last year
- Sparse and discrete interpretability tool for neural networks☆58Updated 11 months ago
- ☆13Updated 10 months ago
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆58Updated 3 months ago
- Implementation of Confidence-Calibrated Adversarial Training (CCAT).☆45Updated 4 years ago
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆67Updated 2 years ago
- Pytorch code for experiments on Linear Transformers☆16Updated last year
- Official implementation for Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds (NeurIPS, 2021).☆22Updated 2 years ago
- ModelDiff: A Framework for Comparing Learning Algorithms☆54Updated last year