f-dangel / backpack
BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.
☆561Updated this week
Related projects ⓘ
Alternatives and complementary repositories for backpack
- Laplace approximations for Deep Learning.☆471Updated this week
- Constrained optimization toolkit for PyTorch☆661Updated 2 years ago
- Efficient PyTorch Hessian eigendecomposition tools!☆364Updated 8 months ago
- ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning☆266Updated last year
- ASDL: Automatic Second-order Differentiation Library for PyTorch☆179Updated 3 months ago
- PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks☆687Updated 7 months ago
- ☆235Updated last year
- ☆153Updated 2 years ago
- PyTorch-based library for Riemannian Manifold Hamiltonian Monte Carlo (RMHMC) and inference in Bayesian neural networks☆425Updated 2 months ago
- PyTorch-SSO: Scalable Second-Order methods in PyTorch☆142Updated last year
- This library would form a permanent home for reusable components for deep probabilistic programming. The library would form and harness a…☆301Updated 3 weeks ago
- KErnel OPerationS, on CPUs and GPUs, with autodiff and without memory overflows☆1,054Updated this week
- Cockpit: A Practical Debugging Tool for Training Deep Neural Networks☆473Updated 2 years ago
- This repository contains the results for the paper: "Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers"☆180Updated 3 years ago
- ☆466Updated 3 months ago
- {KFAC,EKFAC,Diagonal,Implicit} Fisher Matrices and finite width NTKs in PyTorch☆207Updated last month
- Code repo for "A Simple Baseline for Bayesian Uncertainty in Deep Learning"☆454Updated last year
- Optimal transport tools implemented with the JAX framework, to get differentiable, parallel and jit-able computations.☆526Updated this week
- Large-scale, multi-GPU capable, kernel solver☆181Updated 4 months ago
- hessian in pytorch☆185Updated 4 years ago
- Hardware accelerated, batchable and differentiable optimizers in JAX.☆933Updated 2 months ago
- ☆536Updated 2 months ago
- Project site for "Your Classifier is Secretly an Energy-Based Model and You Should Treat it Like One"☆417Updated 2 years ago
- functorch is JAX-like composable function transforms for PyTorch.☆1,396Updated this week
- Hessian spectral density estimation in TF and Jax☆115Updated 4 years ago
- Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions☆258Updated last year
- Code for NeurIPS 2019 paper: "Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes…☆239Updated 4 years ago
- A Machine Learning workflow for Slurm.☆146Updated 3 years ago
- ☆213Updated 2 years ago
- Fast Differentiable Sorting and Ranking☆574Updated 9 months ago