f-dangel / backpackLinks
BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.
☆588Updated 7 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!☆376Updated last year
- Constrained optimization toolkit for PyTorch☆697Updated 3 weeks ago
- Laplace approximations for Deep Learning.☆515Updated 4 months ago
- ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning☆277Updated 2 years ago
- {KFAC,EKFAC,Diagonal,Implicit} Fisher Matrices and finite width NTKs in PyTorch☆215Updated 2 months ago
- ASDL: Automatic Second-order Differentiation Library for PyTorch☆188Updated 8 months ago
- ☆157Updated 3 years ago
- Cockpit: A Practical Debugging Tool for Training Deep Neural Networks☆479Updated 3 years ago
- This library would form a permanent home for reusable components for deep probabilistic programming. The library would form and harness a…☆308Updated 2 months ago
- ☆469Updated 3 months ago
- PyTorch-based library for Riemannian Manifold Hamiltonian Monte Carlo (RMHMC) and inference in Bayesian neural networks☆456Updated 11 months ago
- KErnel OPerationS, on CPUs and GPUs, with autodiff and without memory overflows☆1,119Updated last week
- Hessian spectral density estimation in TF and Jax☆123Updated 4 years ago
- PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks☆750Updated last month
- A Machine Learning workflow for Slurm.☆150Updated 4 years ago
- PyTorch-SSO: Scalable Second-Order methods in PyTorch☆147Updated last year
- Code repo for "A Simple Baseline for Bayesian Uncertainty in Deep Learning"☆470Updated 2 years ago
- ☆241Updated 2 years ago
- Fast Differentiable Sorting and Ranking☆608Updated last year
- Optimal transport tools implemented with the JAX framework, to solve large scale matching problems of any flavor.☆628Updated 2 weeks ago
- hessian in pytorch☆187Updated 4 years ago
- functorch is JAX-like composable function transforms for PyTorch.☆1,436Updated this week
- ☆584Updated last week
- Code for NeurIPS 2019 paper: "Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes…☆245Updated 4 years ago
- Large-scale, multi-GPU capable, kernel solver☆190Updated last month
- Hardware accelerated, batchable and differentiable optimizers in JAX.☆990Updated 4 months ago
- Project site for "Your Classifier is Secretly an Energy-Based Model and You Should Treat it Like One"☆424Updated 2 years ago
- Fast, differentiable sorting and ranking in PyTorch☆827Updated 2 months ago
- [NeurIPS'19] Deep Equilibrium Models☆757Updated 3 years ago
- Repository containing Pytorch code for EKFAC and K-FAC perconditioners.☆146Updated 2 years ago