timgaripov / dnn-mode-connectivityLinks
Mode Connectivity and Fast Geometric Ensembles in PyTorch
☆272Updated 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:
- Efficient PyTorch Hessian eigendecomposition tools!☆375Updated last year
- ☆157Updated 3 years ago
- {KFAC,EKFAC,Diagonal,Implicit} Fisher Matrices and finite width NTKs in PyTorch☆215Updated last month
- NTK reading group☆87Updated 5 years ago
- A pytorch implementation of our jacobian regularizer to encourage learning representations more robust to input perturbations.☆128Updated last year
- Project site for "Your Classifier is Secretly an Energy-Based Model and You Should Treat it Like One"☆424Updated 2 years ago
- Release of CIFAR-10.1, a new test set for CIFAR-10.☆223Updated 5 years ago
- ☆124Updated last year
- ☆59Updated 2 years ago
- ☆192Updated 4 years ago
- Code for experiments in my blog post on the Neural Tangent Kernel: https://eigentales.com/NTK☆176Updated 5 years ago
- Code for "Picking Winning Tickets Before Training by Preserving Gradient Flow" https://openreview.net/pdf?id=SkgsACVKPH☆105Updated 5 years ago
- Code for the paper "Understanding Generalization through Visualizations"☆61Updated 4 years ago
- ☆144Updated 2 years ago
- Pytorch implementation of KFAC and E-KFAC (Natural Gradient).☆132Updated 6 years ago
- Rethinking Bias-Variance Trade-off for Generalization of Neural Networks☆49Updated 4 years ago
- ☆67Updated 6 years ago
- Repository containing Pytorch code for EKFAC and K-FAC perconditioners.☆144Updated 2 years ago
- Learning Sparse Neural Networks through L0 regularization☆245Updated 5 years ago
- Train ImageNet *fast* in 500 lines of code with FFCV☆144Updated last year
- Gradient Starvation: A Learning Proclivity in Neural Networks☆61Updated 4 years ago
- ☆83Updated 5 years ago
- Understanding Training Dynamics of Deep ReLU Networks☆295Updated this week
- Lipschitz Neural Networks described in "Sorting Out Lipschitz Function Approximation" (ICML 2019).☆56Updated 5 years ago
- Create animations for the optimization trajectory of neural nets☆157Updated last year
- Hypergradient descent☆149Updated last year
- PyTorch-SSO: Scalable Second-Order methods in PyTorch☆147Updated last year
- A drop-in replacement for CIFAR-10.☆241Updated 4 years ago
- Approximating neural network loss landscapes in low-dimensional parameter subspaces for PyTorch☆337Updated last year
- Convolutional Neural Tangent Kernel☆113Updated 5 years ago