[ICML 2024] SINGD: KFAC-like Structured Inverse-Free Natural Gradient Descent (http://arxiv.org/abs/2312.05705)
☆24Nov 4, 2024Updated last year
Alternatives and similar repositories for singd
Users that are interested in singd are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Posterior Refinement Improves Sample Efficiency in Bayesian Neural Networks☆11Oct 21, 2022Updated 3 years ago
- [TMLR 2022] Curvature access through the generalized Gauss-Newton's low-rank structure: Eigenvalues, eigenvectors, directional derivative…☆17Jul 19, 2023Updated 3 years ago
- PyTorch linear operators for curvature matrices (Hessian, Fisher/GGN, KFAC, ...)☆71Jul 17, 2026Updated last month
- ☆16Apr 26, 2023Updated 3 years ago
- ASDL: Automatic Second-order Differentiation Library for PyTorch☆192Dec 5, 2024Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Limitations of the Empirical Fisher Approximation☆50Mar 3, 2025Updated last year
- Probabilistic ODE solvers are fun, but are they fast? See also: https://github.com/pnkraemer/probdiffeq for JAX code or https://github.c…☆22Jul 20, 2024Updated 2 years ago
- Code for AISTATS 2017 paper on "Conjugate-Computation Variational Inference"☆20Jul 10, 2020Updated 6 years ago
- BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.