n-gao / pytorch-kfac

Related projects ⓘ

Alternatives and complementary repositories for pytorch-kfac

• kazukiosawa / ngd_in_wide_nn
  simple JAX-/NumPy-based implementations of NGD with exact/approximate Fisher Information Matrix both in parameter-space and function-spac…
  ☆14Updated 4 years ago
• gpauloski / kfac-pytorch
  Distributed K-FAC Preconditioner for PyTorch
  ☆80Updated last week
• alecwangcq / KFAC-Pytorch
  Pytorch implementation of KFAC and E-KFAC (Natural Gradient).
  ☆128Updated 5 years ago
• flaport / torch_eunn
  A Pytorch implementation of an efficient unitary neural network (https://arxiv.org/abs/1612.05231)
  ☆33Updated 4 years ago
• f-dangel / hbp
  Hessian backpropagation (HBP): PyTorch extension of backpropagation for block-diagonal curvature matrix approximations
  ☆20Updated last year
• gaoliyao / Replica_Exchange_Stochastic_Gradient_MCMC
  Code for Non-convex Learning via Replica Exchange Stochastic Gradient MCMC, ICML 2020.
  ☆23Updated 3 years ago
• AlexanderMath / fasth
  Code for the article "What if Neural Networks had SVDs?", to be presented as a spotlight paper at NeurIPS 2020.
  ☆69Updated 4 months ago
• yzhwang / jax-multi-gpu-resnet50-example
  An example showing how to use jax to train resnet50 on multi-node multi-GPU
  ☆20Updated 2 years ago
• mbilos / stribor
  Library for normalizing flows and neural flows.
  ☆24Updated 2 years ago
• SaitejaUtpala / rieoptax
  Riemannian Optimization Using JAX
  ☆45Updated last year
• y1xiaoc / fwdlap
  Forward mode laplacian implemented in JAX tracer
  ☆29Updated 3 weeks ago
• RaphaelArkadyMeyerNYU / HutchPlusPlus
  Code for Hutch++: Optimal Stochastic Trace Estimation
  ☆11Updated 3 years ago
• wangleiphy / MongeAmpereFlow
  Continuous-time gradient flow for generative modeling and variational inference
  ☆29Updated 6 years ago
• eepperly / Randomly-Pivoted-Cholesky
  Code for the paper "Randomly pivoted Cholesky: Practical approximation of a kernel matrix with few entry evaluations"
  ☆25Updated last month
• sail-sg / autofd
  Automatic Functional Differentiation in JAX
  ☆57Updated 9 months ago
• dimitra-maoutsa / odes_for_sdes
  Deterministic particle dynamics for simulating Fokker-Planck probability flows
  ☆24Updated last year
• Information-Fusion-Lab-Umass / NuX
  Normalizing Flows using JAX
  ☆82Updated 11 months ago
• gd-zhang / Weight-Decay
  Regularization, Neural Network Training Dynamics
  ☆14Updated 4 years ago
• fKunstner / limitations-empirical-fisher
  Limitations of the Empirical Fisher Approximation
  ☆45Updated 4 years ago
• microsoft / folx
  Implementation of Forward Laplacian algorithm in JAX
  ☆55Updated 3 weeks ago
• gregversteeg / esh_dynamics
  Hamiltonian Dynamics with Non-Newtonian Momentum for Rapid Sampling
  ☆36Updated 3 years ago
• afqueiruga / StatefulOdeNets
  Refining continuous-in-depth neural networks
  ☆39Updated 3 years ago
• danieljtait / jax_xla_adventures
  Dive into Jax, Flax, XLA and C++
  ☆31Updated 4 years ago
• conormdurkan / lfi
  Neural likelihood-free methods in PyTorch.
  ☆39Updated 4 years ago
• gehring / fax
  ☆78Updated 3 years ago
• thegregyang / NTK4A
  Code for the paper: "Tensor Programs II: Neural Tangent Kernel for Any Architecture"
  ☆97Updated 4 years ago
• google-deepmind / annealed_flow_transport
  ☆49Updated last year
• fmeirinhos / pytorch-hessianfree
  PyTorch implementation of Hessian Free optimisation
  ☆43Updated 4 years ago
• akbir / deq-jax
  [NeurIPS'19] Deep Equilibrium Models Jax Implementation
  ☆38Updated 4 years ago
• locuslab / monotone_op_net
  Monotone operator equilibrium networks
  ☆51Updated 4 years ago