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
- Monotone operator equilibrium networks☆51Updated 4 years ago
- ☆80Updated 3 years ago
- Code for "'Hey, that's not an ODE:' Faster ODE Adjoints via Seminorms" (ICML 2021)☆87Updated 2 years ago
- [NeurIPS'19] Deep Equilibrium Models Jax Implementation☆39Updated 4 years ago
- Natural Gradient, Variational Inference☆29Updated 5 years ago
- Limitations of the Empirical Fisher Approximation☆47Updated last month
- Riemannian Convex Potential Maps☆67Updated 2 years ago
- Neural Fixed-Point Acceleration for Convex Optimization☆29Updated 2 years ago
- Supporting code for the paper "Dangers of Bayesian Model Averaging under Covariate Shift"☆33Updated 2 years ago
- A variational method for fast, approximate inference for stochastic differential equations.☆44Updated 6 years ago
- TensorFlow implementation of "noisy K-FAC" and "noisy EK-FAC".☆60Updated 6 years ago
- Neural likelihood-free methods in PyTorch.☆39Updated 5 years ago
- [NeurIPS 2020] Task-Agnostic Amortized Inference of Gaussian Process Hyperparameters (AHGP)☆21Updated 4 years ago
- Stochastic Gradient Langevin Dynamics for Bayesian learning☆31Updated 3 years ago
- ☆53Updated 9 months ago
- Code required to reproduce the experiments in Auxiliary Variational MCMC☆17Updated 6 years ago
- Course Website☆9Updated 3 years ago
- Code repo for "Function-Space Distributions over Kernels"☆31Updated 4 years ago
- Models and code for the ICLR 2020 workshop paper "Towards Understanding Normalization in Neural ODEs"☆16Updated 4 years ago
- Inference on non-linear dynamical systems written in JAX☆11Updated 4 years ago
- An ultra-lightweight JAX implementation of sparse Gaussian processes via pathwise sampling.☆22Updated 4 years ago
- Code for Knowledge-Adaptation Priors based on the NeurIPS 2021 paper by Khan and Swaroop.☆16Updated 3 years ago
- Code for Unbiased Implicit Variational Inference (UIVI)☆14Updated 6 years ago
- Official code for UnICORNN (ICML 2021)☆27Updated 3 years ago
- Approximate Inference Turns Deep Networks into Gaussian Processes (dnn2gp)☆48Updated 5 years ago
- Code accompanying VarGrad: A Low-Variance Gradient Estimator for Variational Inference☆12Updated 4 years ago
- Code to accompany paper 'Bayesian Deep Ensembles via the Neural Tangent Kernel'☆26Updated 4 years ago
- ☆15Updated 2 years ago
- ☆28Updated 5 years ago