n-gao / pytorch-kfac
Pytorch implementation of KFAC - this is a port of https://github.com/tensorflow/kfac/
☆18Updated 3 months ago
Related projects: ⓘ
- A Pytorch implementation of an efficient unitary neural network (https://arxiv.org/abs/1612.05231)☆32Updated 4 years ago
- simple JAX-/NumPy-based implementations of NGD with exact/approximate Fisher Information Matrix both in parameter-space and function-spac…☆14Updated 3 years ago
- Hessian backpropagation (HBP): PyTorch extension of backpropagation for block-diagonal curvature matrix approximations☆20Updated last year
- Distributed K-FAC Preconditioner for PyTorch☆75Updated last week
- Code for the article "What if Neural Networks had SVDs?", to be presented as a spotlight paper at NeurIPS 2020.☆68Updated last month
- Pytorch implementation of KFAC and E-KFAC (Natural Gradient).☆125Updated 5 years ago
- Hamiltonian Dynamics with Non-Newtonian Momentum for Rapid Sampling☆34Updated 2 years ago
- Code for Non-convex Learning via Replica Exchange Stochastic Gradient MCMC, ICML 2020.☆23Updated 3 years ago
- Riemannian Optimization Using JAX☆44Updated 10 months ago
- An example showing how to use jax to train resnet50 on multi-node multi-GPU☆20Updated 2 years ago
- Library for normalizing flows and neural flows.☆23Updated 2 years ago
- orbital MCMC☆10Updated 3 years ago
- Continuous-time gradient flow for generative modeling and variational inference☆29Updated 5 years ago
- Regularization, Neural Network Training Dynamics☆14Updated 4 years ago
- Neural likelihood-free methods in PyTorch.☆38Updated 4 years ago
- Normalizing Flows using JAX☆82Updated 9 months ago
- Repository containing Pytorch code for EKFAC and K-FAC perconditioners.☆139Updated last year
- ☆78Updated 3 years ago
- Dive into Jax, Flax, XLA and C++☆31Updated 4 years ago
- Code for the paper: "Tensor Programs II: Neural Tangent Kernel for Any Architecture"☆93Updated 4 years ago
- Limitations of the Empirical Fisher Approximation☆45Updated 4 years ago
- Convex potential flows☆78Updated 2 years ago
- Code for Hutch++: Optimal Stochastic Trace Estimation☆11Updated 3 years ago
- ☆11Updated 3 years ago
- scipy linear operators for the Hessian, Fisher/GGN, and more in PyTorch☆17Updated this week
- Bayesian Optimization over Discrete and Mixed Spaces via Probabilistic Reparameterization☆67Updated last year
- Refining continuous-in-depth neural networks☆39Updated 2 years ago
- A Python package for efficient optimisation of real-space renormalization group transformations using Tensorflow.☆27Updated 11 months ago
- ☆29Updated 3 years ago
- Implicit Deep Adaptive Design (iDAD): Policy-Based Experimental Design without Likelihoods☆17Updated 2 years ago