cybertronai / autograd-hacks
☆157Updated 2 years ago
Alternatives and similar repositories for autograd-hacks:
Users that are interested in autograd-hacks are comparing it to the libraries listed below
- Efficient PyTorch Hessian eigendecomposition tools!☆373Updated last year
- Repository containing Pytorch code for EKFAC and K-FAC perconditioners.☆142Updated last year
- Mode Connectivity and Fast Geometric Ensembles in PyTorch☆270Updated 2 years ago
- PyTorch-SSO: Scalable Second-Order methods in PyTorch☆145Updated last year
- Pytorch implementation of KFAC and E-KFAC (Natural Gradient).☆132Updated 5 years ago
- ☆122Updated 11 months ago
- NTK reading group☆88Updated 5 years ago
- Code for the paper: "Tensor Programs II: Neural Tangent Kernel for Any Architecture"☆106Updated 4 years ago
- hessian in pytorch☆187Updated 4 years ago
- Convolutional Neural Tangent Kernel☆111Updated 5 years ago
- Hessian spectral density estimation in TF and Jax☆123Updated 4 years ago
- ☆58Updated 2 years ago
- {KFAC,EKFAC,Diagonal,Implicit} Fisher Matrices and finite width NTKs in PyTorch☆213Updated 2 weeks ago
- This repository is no longer maintained. Check☆81Updated 5 years ago
- ASDL: Automatic Second-order Differentiation Library for PyTorch☆185Updated 5 months ago
- Hypergradient descent☆146Updated 11 months ago
- ☆133Updated 4 years ago
- Collection of algorithms for approximating Fisher Information Matrix for Natural Gradient (and second order method in general)☆139Updated 5 years ago
- Code for experiments in my blog post on the Neural Tangent Kernel: https://eigentales.com/NTK☆172Updated 5 years ago
- ☆83Updated 5 years ago
- ☆33Updated 4 years ago
- Rethinking Bias-Variance Trade-off for Generalization of Neural Networks☆49Updated 4 years ago
- Reparameterize your PyTorch modules☆71Updated 4 years ago
- Project site for "Your Classifier is Secretly an Energy-Based Model and You Should Treat it Like One"☆423Updated 2 years ago
- ☆190Updated 4 years ago
- ☆99Updated 3 years ago
- Lipschitz Neural Networks described in "Sorting Out Lipschitz Function Approximation" (ICML 2019).☆55Updated 4 years ago
- Code for the article "What if Neural Networks had SVDs?", to be presented as a spotlight paper at NeurIPS 2020.☆75Updated 9 months ago
- ☆144Updated 2 years ago
- BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.☆580Updated 4 months ago