f-dangel / backpackLinks
BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.
☆587Updated 5 months ago
Alternatives and similar repositories for backpack
Users that are interested in backpack are comparing it to the libraries listed below
Sorting:
- Efficient PyTorch Hessian eigendecomposition tools!☆374Updated last year
- Laplace approximations for Deep Learning.☆508Updated 2 months ago
- {KFAC,EKFAC,Diagonal,Implicit} Fisher Matrices and finite width NTKs in PyTorch☆215Updated this week
- Constrained optimization toolkit for PyTorch☆682Updated 3 years ago
- ASDL: Automatic Second-order Differentiation Library for PyTorch☆188Updated 6 months ago
- PyTorch-based library for Riemannian Manifold Hamiltonian Monte Carlo (RMHMC) and inference in Bayesian neural networks☆450Updated 9 months ago
- ☆470Updated last month
- ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning☆277Updated 2 years ago
- KErnel OPerationS, on CPUs and GPUs, with autodiff and without memory overflows☆1,099Updated this week
- This library would form a permanent home for reusable components for deep probabilistic programming. The library would form and harness a…☆305Updated 3 weeks ago
- ☆241Updated 2 years ago
- PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks☆743Updated last year
- Project site for "Your Classifier is Secretly an Energy-Based Model and You Should Treat it Like One"☆423Updated 2 years ago
- Code repo for "A Simple Baseline for Bayesian Uncertainty in Deep Learning"☆464Updated last year
- ☆157Updated 3 years ago
- PyTorch-SSO: Scalable Second-Order methods in PyTorch☆146Updated last year
- Hardware accelerated, batchable and differentiable optimizers in JAX.☆974Updated 2 months ago
- Optimal transport tools implemented with the JAX framework, to solve large scale matching problems of any flavor.☆604Updated 2 weeks ago
- Cockpit: A Practical Debugging Tool for Training Deep Neural Networks☆480Updated 2 years ago
- functorch is JAX-like composable function transforms for PyTorch.☆1,432Updated this week
- ☆578Updated last month
- hessian in pytorch☆187Updated 4 years ago
- A PyTorch implementation of L-BFGS.☆602Updated 2 years ago
- A Machine Learning workflow for Slurm.☆149Updated 4 years ago
- This repository contains the results for the paper: "Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers"☆180Updated 3 years ago
- Repository containing Pytorch code for EKFAC and K-FAC perconditioners.☆143Updated 2 years ago
- Hessian spectral density estimation in TF and Jax☆123Updated 4 years ago
- Approximating neural network loss landscapes in low-dimensional parameter subspaces for PyTorch☆335Updated last year
- Compositional Linear Algebra☆476Updated 3 weeks ago
- Large-scale, multi-GPU capable, kernel solver☆189Updated 11 months ago