99991 / cifar10-fast-simpleLinks
Train CIFAR10 to 94% accuracy in a few minutes/seconds. Based on https://github.com/davidcpage/cifar10-fast
☆22Updated 2 years ago
Alternatives and similar repositories for cifar10-fast-simple
Users that are interested in cifar10-fast-simple are comparing it to the libraries listed below
Sorting:
- ☆157Updated 3 years ago
- Efficient PyTorch Hessian eigendecomposition tools!☆379Updated last year
- {KFAC,EKFAC,Diagonal,Implicit} Fisher Matrices and finite width NTKs in PyTorch☆215Updated 2 months ago
- Pytorch implementation of KFAC and E-KFAC (Natural Gradient).☆132Updated 6 years ago
- ASDL: Automatic Second-order Differentiation Library for PyTorch☆190Updated 11 months ago
- Hessian spectral density estimation in TF and Jax☆124Updated 5 years ago
- ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning☆281Updated 2 years ago
- Code for the paper: "Tensor Programs II: Neural Tangent Kernel for Any Architecture"☆104Updated 5 years ago
- Convolutional Neural Tangent Kernel☆112Updated 6 years ago
- ☆194Updated 4 years ago
- ☆15Updated 5 years ago
- Mode Connectivity and Fast Geometric Ensembles in PyTorch☆277Updated 3 years ago
- ☆83Updated 5 years ago
- Code for experiments in my blog post on the Neural Tangent Kernel: https://eigentales.com/NTK☆173Updated 5 years ago
- PyTorch linear operators for curvature matrices (Hessian, Fisher/GGN, KFAC, ...)☆57Updated last week
- Create animations for the optimization trajectory of neural nets☆161Updated last year
- PyTorch implementation of Hessian Free optimisation☆43Updated 5 years ago
- Butterfly matrix multiplication in PyTorch☆174Updated 2 years ago
- Distributed K-FAC preconditioner for PyTorch☆91Updated this week
- PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks☆760Updated 4 months ago
- Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation precondition…☆188Updated 3 weeks ago
- Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians (ICML 2019)☆16Updated 6 years ago
- Parameter-Free Optimizers for Pytorch☆131Updated last year
- Code for "Picking Winning Tickets Before Training by Preserving Gradient Flow" https://openreview.net/pdf?id=SkgsACVKPH☆105Updated 5 years ago
- PyTorch-SSO: Scalable Second-Order methods in PyTorch☆147Updated 2 years ago
- Algorithms for Privacy-Preserving Machine Learning in JAX☆107Updated this week
- DeepOBS: A Deep Learning Optimizer Benchmark Suite☆108Updated last year
- ☆59Updated 2 years ago
- NTK reading group☆87Updated 5 years ago
- BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.☆595Updated 10 months ago