kazukiosawa / ngd_in_wide_nn
simple JAX-/NumPy-based implementations of NGD with exact/approximate Fisher Information Matrix both in parameter-space and function-space (by empirical/analytical NTK).
☆14Updated 4 years ago
Alternatives and similar repositories for ngd_in_wide_nn:
Users that are interested in ngd_in_wide_nn are comparing it to the libraries listed below
- Implicit Deep Adaptive Design (iDAD): Policy-Based Experimental Design without Likelihoods☆19Updated 3 years ago
- Official code for UnICORNN (ICML 2021)☆27Updated 3 years ago
- ☆80Updated 3 years ago
- Neural likelihood-free methods in PyTorch.☆39Updated 5 years ago
- Stochastic Gradient Langevin Dynamics for Bayesian learning☆30Updated 3 years ago
- Limitations of the Empirical Fisher Approximation☆47Updated 2 weeks ago
- Code for Unbiased Implicit Variational Inference (UIVI)☆14Updated 6 years ago
- Monotone operator equilibrium networks☆51Updated 4 years ago
- Variational Auto-Regressive Gaussian Processes for Continual Learning☆21Updated 3 years ago
- Code for "'Hey, that's not an ODE:' Faster ODE Adjoints via Seminorms" (ICML 2021)☆86Updated 2 years ago
- Code repo for "Function-Space Distributions over Kernels"☆31Updated 4 years ago
- Repository for DTU Special Course, focusing on Variational Inference using Normalizing Flows (VINF). Supervised by Michael Riis Andersen☆25Updated 4 years ago
- Approximate Inference Turns Deep Networks into Gaussian Processes (dnn2gp)☆48Updated 5 years ago
- A pytorch version of hamiltonian monte carlo☆14Updated 5 years ago
- Natural Gradient, Variational Inference☆29Updated 5 years ago
- [NeurIPS'19] Deep Equilibrium Models Jax Implementation☆39Updated 4 years ago
- TensorFlow implementation of "noisy K-FAC" and "noisy EK-FAC".☆60Updated 6 years ago
- Code to accompany paper 'Bayesian Deep Ensembles via the Neural Tangent Kernel'☆27Updated 4 years ago
- Supporting code for the paper "Dangers of Bayesian Model Averaging under Covariate Shift"☆33Updated 2 years ago
- Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design☆30Updated 3 years ago
- Contains code for the NeurIPS 2020 paper by Pan et al., "Continual Deep Learning by FunctionalRegularisation of Memorable Past"☆44Updated 4 years ago
- Neural Fixed-Point Acceleration for Convex Optimization☆29Updated 2 years ago
- ☆53Updated 7 months ago
- Meta-learning Gaussian process (GP) priors via PAC-Bayes bounds☆25Updated last year
- Probabilistic Solution of Differential Equations☆13Updated 2 years ago
- Code release for the ICLR paper☆20Updated 6 years ago
- Course Website☆9Updated 3 years ago
- A differentiation API for PyTorch☆30Updated 4 years ago
- Riemannian Convex Potential Maps☆67Updated last year
- Demos for the paper Generalized Variational Inference (Knoblauch, Jewson & Damoulas, 2019)☆20Updated 5 years ago