n-gao / pytorch-kfac
Pytorch implementation of KFAC - this is a port of https://github.com/tensorflow/kfac/
☆23Updated 9 months ago
Alternatives and similar repositories for pytorch-kfac:
Users that are interested in pytorch-kfac are comparing it to the libraries listed below
- Pytorch implementation of KFAC and E-KFAC (Natural Gradient).☆130Updated 5 years ago
- Code for the article "What if Neural Networks had SVDs?", to be presented as a spotlight paper at NeurIPS 2020.☆73Updated 7 months ago
- Hessian backpropagation (HBP): PyTorch extension of backpropagation for block-diagonal curvature matrix approximations☆20Updated last year
- Distributed K-FAC Preconditioner for PyTorch☆85Updated this week
- An example showing how to use jax to train resnet50 on multi-node multi-GPU☆20Updated 2 years ago
- A Pytorch implementation of an efficient unitary neural network (https://arxiv.org/abs/1612.05231)☆33Updated 4 years ago
- simple JAX-/NumPy-based implementations of NGD with exact/approximate Fisher Information Matrix both in parameter-space and function-spac…☆14Updated 4 years ago
- Continuous-time gradient flow for generative modeling and variational inference☆30Updated 6 years ago
- Simple CIFAR10 ResNet example with JAX.☆23Updated 3 years ago
- Repository containing Pytorch code for EKFAC and K-FAC perconditioners.☆141Updated last year
- PyTorch implementation of Hessian Free optimisation☆43Updated 5 years ago
- Fast extremal eigensolvers for PyTorch.☆17Updated 3 years ago
- Code for Non-convex Learning via Replica Exchange Stochastic Gradient MCMC, ICML 2020.☆24Updated 4 years ago
- ☆65Updated 2 months ago
- Normalizing Flows with a resampled base distribution☆44Updated 2 years ago
- Package for CGD and ACGD optimizers☆20Updated 2 years ago
- Riemannian Optimization Using JAX☆48Updated last year
- Improved LBFGS and LBFGS-B optimizers in PyTorch.☆59Updated 4 months ago
- PyTorch AutoNEB implementation to identify minimum energy paths, e.g. in neural network loss landscapes☆54Updated 2 years ago
- ☆67Updated 2 years ago
- Sampling with gradient-based Markov Chain Monte Carlo approaches☆97Updated 10 months ago
- Hamiltonian Dynamics with Non-Newtonian Momentum for Rapid Sampling☆36Updated 3 years ago
- Stochastic Normalizing Flows☆76Updated 3 years ago
- ☆28Updated 3 years ago
- Refining continuous-in-depth neural networks☆39Updated 3 years ago
- Experiments for Meta-Learning Symmetries by Reparameterization☆56Updated 3 years ago
- Implementation of Action Matching☆38Updated last year
- Regularization, Neural Network Training Dynamics☆14Updated 5 years ago
- Convex potential flows☆83Updated 3 years ago
- Limitations of the Empirical Fisher Approximation☆47Updated this week