mansheej / lth_diet
☆10Updated 2 years ago
Alternatives and similar repositories for lth_diet:
Users that are interested in lth_diet are comparing it to the libraries listed below
- ☆35Updated last year
- ☆36Updated 3 years ago
- ☆19Updated 2 years ago
- ☆17Updated 2 years ago
- Codebase for Mechanistic Mode Connectivity☆13Updated last year
- ModelDiff: A Framework for Comparing Learning Algorithms☆56Updated last year
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆43Updated last year
- Replicating and dissecting the git-re-basin project in one-click-replication Colabs☆36Updated 2 years ago
- Code accompanying our paper "Feature Learning in Infinite-Width Neural Networks" (https://arxiv.org/abs/2011.14522)☆61Updated 3 years ago
- This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…☆36Updated 2 years ago
- SGD with large step sizes learns sparse features [ICML 2023]☆32Updated last year
- Towards Understanding Sharpness-Aware Minimization [ICML 2022]☆35Updated 2 years ago
- ☆44Updated 2 years ago
- Quantification of Uncertainty with Adversarial Models☆28Updated last year
- ☆54Updated 4 years ago
- CIFAR10 ResNets implemented in JAX+Flax☆12Updated 2 years ago
- Source code of "What can linearized neural networks actually say about generalization?☆20Updated 3 years ago
- Code for the paper "The Journey, Not the Destination: How Data Guides Diffusion Models"☆22Updated last year
- ☆65Updated 3 months ago
- ☆18Updated 8 months ago
- ☆27Updated 2 years ago
- 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
- Official code for the paper: "Metadata Archaeology"☆19Updated last year
- Public Codebase for Rethinking Parameter Counting: Effective Dimensionality Revisited☆37Updated 2 years ago
- Deep Learning & Information Bottleneck☆58Updated last year
- Notebooks for managing NeurIPS 2014 and analysing the NeurIPS experiment.☆11Updated 10 months ago
- Pytorch code for "Improving Self-Supervised Learning by Characterizing Idealized Representations"☆40Updated 2 years ago
- ☆22Updated 6 months ago
- Official code for the paper "Compositional Generalization from First Principles" (NeurIPS 2023)☆10Updated last year
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆58Updated last year