timgaripov / dnn-mode-connectivityLinks
Mode Connectivity and Fast Geometric Ensembles in PyTorch
☆271Updated 2 years ago
Alternatives and similar repositories for dnn-mode-connectivity
Users that are interested in dnn-mode-connectivity are comparing it to the libraries listed below
Sorting:
- ☆157Updated 3 years ago
- Efficient PyTorch Hessian eigendecomposition tools!☆374Updated last year
- NTK reading group☆87Updated 5 years ago
- ☆123Updated last year
- Rethinking Bias-Variance Trade-off for Generalization of Neural Networks☆49Updated 4 years ago
- Release of CIFAR-10.1, a new test set for CIFAR-10.☆223Updated 5 years ago
- Code for "Picking Winning Tickets Before Training by Preserving Gradient Flow" https://openreview.net/pdf?id=SkgsACVKPH☆105Updated 5 years ago
- Project site for "Your Classifier is Secretly an Energy-Based Model and You Should Treat it Like One"☆423Updated 2 years ago
- {KFAC,EKFAC,Diagonal,Implicit} Fisher Matrices and finite width NTKs in PyTorch☆215Updated last week
- ☆133Updated 4 years ago
- Convolutional Neural Tangent Kernel☆111Updated 5 years ago
- Pytorch implementation of KFAC and E-KFAC (Natural Gradient).☆132Updated 5 years ago
- A pytorch implementation of our jacobian regularizer to encourage learning representations more robust to input perturbations.☆128Updated last year
- Code for experiments in my blog post on the Neural Tangent Kernel: https://eigentales.com/NTK☆175Updated 5 years ago
- PyTorch-SSO: Scalable Second-Order methods in PyTorch☆146Updated last year
- Repository containing Pytorch code for EKFAC and K-FAC perconditioners.☆143Updated 2 years ago
- Train ImageNet *fast* in 500 lines of code with FFCV☆143Updated last year
- ☆190Updated 4 years ago
- ☆58Updated 2 years ago
- ☆175Updated 11 months ago
- Code for "Supermasks in Superposition"☆124Updated last year
- A drop-in replacement for CIFAR-10.☆241Updated 4 years ago
- Code for the paper: "Tensor Programs II: Neural Tangent Kernel for Any Architecture"☆105Updated 4 years ago
- Learning Sparse Neural Networks through L0 regularization☆241Updated 4 years ago
- hessian in pytorch☆187Updated 4 years ago
- Approximating neural network loss landscapes in low-dimensional parameter subspaces for PyTorch☆335Updated last year
- Lipschitz Neural Networks described in "Sorting Out Lipschitz Function Approximation" (ICML 2019).☆56Updated 5 years ago
- Reparameterize your PyTorch modules☆71Updated 4 years ago
- ☆144Updated 2 years ago
- Gradient Starvation: A Learning Proclivity in Neural Networks☆61Updated 4 years ago