thegregyang / GP4A
Code for NeurIPS 2019 paper: "Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes"
☆236Updated 4 years ago
Related projects: ⓘ
- ☆157Updated last month
- [IJCAI'19, NeurIPS'19] Anode: Unconditionally Accurate Memory-Efficient Gradients for Neural ODEs☆103Updated 3 years ago
- PyTorch-SSO: Scalable Second-Order methods in PyTorch☆141Updated 11 months ago
- Hessian spectral density estimation in TF and Jax☆112Updated 4 years ago
- hessian in pytorch☆185Updated 3 years ago
- Efficient PyTorch Hessian eigendecomposition tools!☆355Updated 6 months ago
- ASDL: Automatic Second-order Differentiation Library for PyTorch☆176Updated last month
- {KFAC,EKFAC,Diagonal,Implicit} Fisher Matrices and finite width NTKs in PyTorch☆204Updated last month
- Convolutional Neural Tangent Kernel☆108Updated 4 years ago
- Code for experiments in my blog post on the Neural Tangent Kernel: https://rajatvd.github.io/NTK☆166Updated 4 years ago
- Code for the paper: "Tensor Programs II: Neural Tangent Kernel for Any Architecture"☆93Updated 4 years ago
- Optimization with orthogonal constraints and on general manifolds☆123Updated 4 years ago
- Repository containing Pytorch code for EKFAC and K-FAC perconditioners.☆139Updated last year
- Pytorch implementation of preconditioned stochastic gradient descent (affine group preconditioner, low-rank approximation preconditioner …☆105Updated this week
- ☆177Updated 5 years ago
- Hypergradient descent☆137Updated 3 months ago
- paper lists and information on mean-field theory of deep learning☆75Updated 5 years ago
- Implementation of Model-Agnostic Meta-Learning (MAML) in Jax☆188Updated last year
- Understanding normalizing flows☆131Updated 4 years ago
- ☆156Updated 4 years ago
- ☆58Updated 5 years ago
- Experiment code for "Randomized Automatic Differentiation"☆67Updated 4 years ago
- Code for the paper "Learning Differential Equations that are Easy to Solve"☆265Updated 2 years ago
- BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.☆555Updated 4 months ago
- ☆231Updated last year
- Pytorch implementation of Block Neural Autoregressive Flow☆175Updated 3 years ago
- ☆215Updated 2 years ago
- Normalizing Flows in Jax☆105Updated 4 years ago
- ☆257Updated last year
- Code for "Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations"☆167Updated 2 years ago