orobix / fwdgradLinks
Implementation of "Gradients without backpropagation" paper (https://arxiv.org/abs/2202.08587) using functorch
☆114Updated 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☆93Updated this week
- Create animations for the optimization trajectory of neural nets☆161Updated last year
- Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation precondition…☆191Updated last week
- ☆222Updated 2 years ago
- ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning☆283Updated 2 years ago
- ASDL: Automatic Second-order Differentiation Library for PyTorch☆191Updated last year
- Butterfly matrix multiplication in PyTorch☆178Updated 2 years ago
- ☆73Updated last year
- Easy-to-use AdaHessian optimizer (PyTorch)☆79Updated 5 years ago
- ☆233Updated 11 months ago
- Structured matrices for compressing neural networks☆67Updated 2 years ago
- Code for the paper: "Tensor Programs II: Neural Tangent Kernel for Any Architecture"☆106Updated 5 years ago
- Efficient Riemannian Optimization on Stiefel Manifold via Cayley Transform☆44Updated 6 years ago
- ☆68Updated 6 years ago
- Pytorch implementation of KFAC and E-KFAC (Natural Gradient).☆132Updated 6 years ago
- {KFAC,EKFAC,Diagonal,Implicit} Fisher Matrices and finite width NTKs in PyTorch☆217Updated last month
- A custom PyTorch layer that is capable of implementing extremely wide and sparse linear layers efficiently☆51Updated 2 years ago
- ☆59Updated 5 years ago
- Code release for REPAIR: REnormalizing Permuted Activations for Interpolation Repair☆52Updated last year
- Visualizing the the loss landscape of Fully-Connected Neural Networks☆46Updated 2 years ago
- Collect optimizer related papers, data, repositories☆99Updated last year
- Non official implementation of the Linear Recurrent Unit (LRU, Orvieto et al. 2023)☆61Updated 4 months ago
- Sequence Modeling with Multiresolution Convolutional Memory (ICML 2023)☆127Updated 2 years ago
- Lightweight torch implementation of rigl, a sparse-to-sparse optimizer.☆60Updated 4 years ago
- Gaussian-Bernoulli Restricted Boltzmann Machines☆106Updated 3 years ago
- Code for the article "What if Neural Networks had SVDs?", to be presented as a spotlight paper at NeurIPS 2020.☆77Updated last year
- ☆66Updated 4 years ago
- Parameter-Free Optimizers for Pytorch☆130Updated last year
- Study on the applicability of Direct Feedback Alignment to neural view synthesis, recommender systems, geometric learning, and natural la…☆89Updated 3 years ago
- [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