orobix / fwdgrad
Implementation of "Gradients without backpropagation" paper (https://arxiv.org/abs/2202.08587) using functorch
☆108Updated last year
Alternatives and similar repositories for fwdgrad:
Users that are interested in fwdgrad are comparing it to the libraries listed below
- Distributed K-FAC Preconditioner for PyTorch☆85Updated this week
- {KFAC,EKFAC,Diagonal,Implicit} Fisher Matrices and finite width NTKs in PyTorch☆211Updated this week
- ☆60Updated 3 years ago
- Code for the article "What if Neural Networks had SVDs?", to be presented as a spotlight paper at NeurIPS 2020.☆73Updated 7 months ago
- ☆201Updated 2 years ago
- PyTorch implementation of Mixer-nano (#parameters is 0.67M, originally Mixer-S/16 has 18M) with 90.83 % acc. on CIFAR-10. Training from s…☆30Updated 3 years ago
- Create animations for the optimization trajectory of neural nets☆145Updated last year
- Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation precondition…☆168Updated 2 months ago
- Pytorch implementation of KFAC and E-KFAC (Natural Gradient).☆130Updated 5 years ago
- Easy Hypernetworks in Pytorch and Jax☆97Updated 2 years ago
- Lightweight torch implementation of rigl, a sparse-to-sparse optimizer.☆56Updated 3 years ago
- ASDL: Automatic Second-order Differentiation Library for PyTorch☆184Updated 2 months ago
- ☆65Updated 2 months ago
- ☆219Updated 2 weeks ago
- Implementations and checkpoints for ResNet, Wide ResNet, ResNeXt, ResNet-D, and ResNeSt in JAX (Flax).☆107Updated 2 years ago
- Code for the paper: Why Transformers Need Adam: A Hessian Perspective☆50Updated 10 months ago
- Accelerated First Order Parallel Associative Scan☆172Updated 6 months ago
- ☆161Updated 3 months ago
- ☆67Updated 5 years ago
- Structured matrices for compressing neural networks☆66Updated last year
- ☆36Updated last year
- Sequence Modeling with Multiresolution Convolutional Memory (ICML 2023)☆122Updated last year
- This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…☆35Updated 2 years ago
- PyTorch linear operators for curvature matrices (Hessian, Fisher/GGN, KFAC, ...)☆32Updated this week
- ☆54Updated 7 months ago
- Parallelizing non-linear sequential models over the sequence length☆51Updated last month
- ☆17Updated 8 months ago
- Forward Pass Learning and Inference Library, for neural networks and general intelligence, Signal Propagation (sigprop)☆51Updated last year
- Non official implementation of the Linear Recurrent Unit (LRU, Orvieto et al. 2023)☆53Updated 3 months ago
- PyTorch implementation of HashedNets☆36Updated last year