orobix / fwdgradLinks
Implementation of "Gradients without backpropagation" paper (https://arxiv.org/abs/2202.08587) using functorch
☆113Updated 2 years ago
Alternatives and similar repositories for fwdgrad
Users that are interested in fwdgrad are comparing it to the libraries listed below
Sorting:
- Distributed K-FAC preconditioner for PyTorch☆90Updated last week
- ☆218Updated 2 years ago
- Butterfly matrix multiplication in PyTorch☆174Updated 2 years ago
- Lightweight torch implementation of rigl, a sparse-to-sparse optimizer.☆58Updated 3 years ago
- ☆233Updated 7 months ago
- Efficient Riemannian Optimization on Stiefel Manifold via Cayley Transform☆42Updated 6 years ago
- Create animations for the optimization trajectory of neural nets☆159Updated last year
- ASDL: Automatic Second-order Differentiation Library for PyTorch☆190Updated 10 months ago
- Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation precondition…☆183Updated last week
- Collect optimizer related papers, data, repositories☆97Updated 10 months ago
- ☆70Updated 10 months ago
- {KFAC,EKFAC,Diagonal,Implicit} Fisher Matrices and finite width NTKs in PyTorch☆215Updated last month
- Pytorch implementation of KFAC and E-KFAC (Natural Gradient).☆131Updated 6 years ago
- A custom PyTorch layer that is capable of implementing extremely wide and sparse linear layers efficiently☆51Updated last year
- ☆55Updated last year
- ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning☆282Updated 2 years ago
- Structured matrices for compressing neural networks☆67Updated 2 years ago
- Easy Hypernetworks in Pytorch and Jax☆105Updated 2 years ago
- Study on the applicability of Direct Feedback Alignment to neural view synthesis, recommender systems, geometric learning, and natural la…☆90Updated 3 years ago
- Parallelizing non-linear sequential models over the sequence length☆54Updated 3 months ago
- ☆39Updated last year
- Rational Activation Functions - Replacing Padé Activation Units☆99Updated 6 months ago
- ☆65Updated 3 years ago
- Code for the paper: "Tensor Programs II: Neural Tangent Kernel for Any Architecture"☆105Updated 5 years ago
- ☆58Updated last year
- [ICML2022] Training Your Sparse Neural Network Better with Any Mask. Ajay Jaiswal, Haoyu Ma, Tianlong Chen, ying Ding, and Zhangyang Wang☆30Updated 3 years ago
- Code for the article "What if Neural Networks had SVDs?", to be presented as a spotlight paper at NeurIPS 2020.☆76Updated last year
- Code for the paper: Why Transformers Need Adam: A Hessian Perspective☆63Updated 6 months ago
- Accelerated First Order Parallel Associative Scan☆190Updated last year
- ☆185Updated last year