f-dangel / vivit
[TMLR 2022] Curvature access through the generalized Gauss-Newton's low-rank structure: Eigenvalues, eigenvectors, directional derivatives & Newton steps
☆17Updated last year
Alternatives and similar repositories for vivit:
Users that are interested in vivit are comparing it to the libraries listed below
- [ICML 2024] SINGD: KFAC-like Structured Inverse-Free Natural Gradient Descent (http://arxiv.org/abs/2312.05705)☆21Updated 2 months ago
- Riemannian Optimization Using JAX☆47Updated last year
- Source code for my PhD thesis: Backpropagation Beyond the Gradient☆20Updated last year
- Convolutions and more as einsum for PyTorch☆13Updated 7 months ago
- Visualize, create, and operate on pytrees in the most intuitive way possible.☆43Updated this week
- PyTorch linear operators for curvature matrices (Hessian, Fisher/GGN, KFAC, ...)☆24Updated this week
- [ICML 2024] SIRFShampoo: Structured inverse- and root-free Shampoo in PyTorch (https://arxiv.org/abs/2402.03496)☆14Updated 2 months ago
- ☆15Updated 4 years ago
- code for "Semi-Discrete Normalizing Flows through Differentiable Tessellation"☆24Updated 2 years ago
- Convex potential flows☆81Updated 3 years ago
- Supplementary code for the paper "Stationary Kernels and Gaussian Processes on Lie Groups and their Homogeneous Spaces"☆42Updated last year
- Code for 'Periodic Activation Functions Induce Stationarity' (NeurIPS 2021)☆18Updated 3 years ago
- ☆15Updated last year
- code for "Neural Conservation Laws A Divergence-Free Perspective".☆35Updated 2 years ago
- Implementation of Action Matching for the Schrödinger equation☆24Updated last year
- Code for "'Hey, that's not an ODE:' Faster ODE Adjoints via Seminorms" (ICML 2021)☆86Updated 2 years ago
- Fine-grained, dynamic control of neural network topology in JAX.☆21Updated last year
- PyTorch implementation of Continuously Indexed Flows paper, with many baseline normalising flows☆31Updated 3 years ago
- Open source code for EigenGame.☆29Updated last year
- Efficient Householder Transformation in PyTorch☆63Updated 3 years ago
- Matrix-free linear algebra in JAX.☆113Updated last week
- Riemannian Convex Potential Maps☆67Updated last year
- Laplace approximated BNN surrogate for BoTorch☆8Updated 2 months ago
- ☆33Updated last year
- Wraps PyTorch code in a JIT-compatible way for JAX. Supports automatically defining gradients for reverse-mode AutoDiff.☆43Updated last week
- Code for the article "What if Neural Networks had SVDs?", to be presented as a spotlight paper at NeurIPS 2020.☆72Updated 5 months ago
- Pytorch implementation of SuperPolyak subgradient method.☆43Updated 2 years ago
- Normalizing Flows using JAX☆82Updated last year
- Running Jax in PyTorch Lightning☆83Updated last month
- JAX exponential map normalising flows on sphere☆17Updated 4 years ago