gpauloski / kfac-pytorch
Distributed K-FAC Preconditioner for PyTorch
☆85Updated this week
Alternatives and similar repositories for kfac-pytorch:
Users that are interested in kfac-pytorch are comparing it to the libraries listed below
- Pytorch implementation of KFAC and E-KFAC (Natural Gradient).☆130Updated 5 years ago
- Code for the article "What if Neural Networks had SVDs?", to be presented as a spotlight paper at NeurIPS 2020.☆74Updated 7 months ago
- Pytorch implementation of KFAC - this is a port of https://github.com/tensorflow/kfac/☆23Updated 9 months ago
- Sparsity support for PyTorch☆35Updated last month
- Efficient Riemannian Optimization on Stiefel Manifold via Cayley Transform☆38Updated 5 years ago
- ASDL: Automatic Second-order Differentiation Library for PyTorch☆185Updated 3 months ago
- Limitations of the Empirical Fisher Approximation☆47Updated last week
- A Chainer extension for K-FAC☆20Updated 5 years ago
- 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
- Repository containing Pytorch code for EKFAC and K-FAC perconditioners.☆141Updated last year
- Structured matrices for compressing neural networks☆66Updated last year
- Butterfly matrix multiplication in PyTorch☆167Updated last year
- ☆47Updated 5 years ago
- ☆65Updated 3 months ago
- ☆35Updated 3 months ago
- Hessian backpropagation (HBP): PyTorch extension of backpropagation for block-diagonal curvature matrix approximations☆20Updated last year
- Simple CIFAR10 ResNet example with JAX.☆23Updated 3 years ago
- Code base for SRSGD.☆28Updated 5 years ago
- ☆11Updated 2 years ago
- Computing gradients and Hessians of feed-forward networks with GPU acceleration☆18Updated last year
- {KFAC,EKFAC,Diagonal,Implicit} Fisher Matrices and finite width NTKs in PyTorch☆211Updated this week
- ☆29Updated 4 years ago
- Code accompanying the NeurIPS 2020 paper: WoodFisher (Singh & Alistarh, 2020)☆48Updated 4 years ago
- ☆67Updated 5 years ago
- Source code of "What can linearized neural networks actually say about generalization?☆20Updated 3 years ago
- Create animations for the optimization trajectory of neural nets☆146Updated last year
- Code for the paper: Why Transformers Need Adam: A Hessian Perspective☆51Updated this week
- Lightweight torch implementation of rigl, a sparse-to-sparse optimizer.☆56Updated 3 years ago
- [ICLR 2023] Eva: Practical Second-order Optimization with Kronecker-vectorized Approximation☆12Updated last year