edwardjhu / TP4
Code accompanying our paper "Feature Learning in Infinite-Width Neural Networks" (https://arxiv.org/abs/2011.14522)
☆61Updated 3 years ago
Alternatives and similar repositories for TP4:
Users that are interested in TP4 are comparing it to the libraries listed below
- Code for the paper: "Tensor Programs II: Neural Tangent Kernel for Any Architecture"☆105Updated 4 years ago
- Hessian spectral density estimation in TF and Jax☆122Updated 4 years ago
- ☆65Updated 3 months ago
- ☆99Updated 3 years ago
- A centralized place for deep thinking code and experiments☆82Updated last year
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆76Updated 2 years ago
- ☆60Updated 3 years ago
- PyTorch implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆36Updated 3 years ago
- Structured matrices for compressing neural networks☆66Updated last year
- Convolutional Neural Tangent Kernel☆109Updated 5 years ago
- ☆66Updated 6 years ago
- Source code of "What can linearized neural networks actually say about generalization?☆20Updated 3 years ago
- ☆49Updated 4 years ago
- Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"☆60Updated 3 years ago
- Replicating and dissecting the git-re-basin project in one-click-replication Colabs☆36Updated 2 years ago
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆43Updated last year
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆58Updated last year
- DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule☆60Updated last year
- codebase for "A Theory of the Inductive Bias and Generalization of Kernel Regression and Wide Neural Networks"☆50Updated last year
- A custom PyTorch layer that is capable of implementing extremely wide and sparse linear layers efficiently☆49Updated last year
- ☆35Updated last year
- SGD with large step sizes learns sparse features [ICML 2023]☆32Updated last year
- ☆24Updated 2 years ago
- Pytorch implementation of KFAC and E-KFAC (Natural Gradient).☆130Updated 5 years ago
- NTK reading group☆88Updated 5 years ago
- The official repository for our paper "The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers". We s…☆67Updated 2 years ago
- Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation precondition…☆170Updated 3 months ago
- ☆29Updated 4 years ago
- Code for testing DCT plus Sparse (DCTpS) networks☆14Updated 3 years ago
- Official implementation of "Multi-scale Feature Learning Dynamics: Insights for Double Descent".☆16Updated 2 years ago