wiseodd / natural-gradients
Collection of algorithms for approximating Fisher Information Matrix for Natural Gradient (and second order method in general)
☆138Updated 5 years ago
Alternatives and similar repositories for natural-gradients:
Users that are interested in natural-gradients are comparing it to the libraries listed below
- Convolutional Neural Tangent Kernel☆109Updated 5 years ago
- Repository containing Pytorch code for EKFAC and K-FAC perconditioners.☆141Updated last year
- ☆133Updated 7 years ago
- Limitations of the Empirical Fisher Approximation☆47Updated 2 weeks ago
- paper lists and information on mean-field theory of deep learning☆75Updated 5 years ago
- NTK reading group☆88Updated 5 years ago
- hessian in pytorch☆187Updated 4 years ago
- Hypergradient descent☆145Updated 9 months ago
- Geometric Certifications of Neural Nets☆41Updated 2 years ago
- Testing Nerual Tangent Kernel (NTK) on small UCI datasets☆84Updated 5 years ago
- This repository is no longer maintained. Check☆81Updated 4 years ago
- pyhessian is a TensorFlow module which can be used to estimate Hessian matrices☆24Updated 3 years ago
- ☆166Updated 7 months ago
- Lua implementation of Entropy-SGD☆81Updated 6 years ago
- A tensorflow implementation of VAE training with Renyi divergence☆31Updated 8 years ago
- a python implementation of various versions of the information bottleneck, including automated parameter searching☆123Updated 4 years ago
- Code for "A Spectral Approach to Gradient Estimation for Implicit Distributions" (ICML'18)☆33Updated last year
- Hessian spectral density estimation in TF and Jax☆122Updated 4 years ago
- Code for "Functional variational Bayesian neural networks" (https://arxiv.org/abs/1903.05779)☆82Updated 4 years ago
- Sample code for running deterministic variational inference to train Bayesian neural networks☆100Updated 6 years ago
- Scalable Training of Inference Networks for Gaussian-Process Models, ICML 2019☆41Updated 2 years ago
- ☆122Updated 9 months ago
- Computing various norms/measures on over-parametrized neural networks☆49Updated 6 years ago
- Implementation of Methods Proposed in Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks (NeurIPS 2019)☆34Updated 4 years ago
- ☆36Updated 3 years ago
- ☆152Updated 4 years ago
- Code for the paper Implicit Weight Uncertainty in Neural Networks☆65Updated 5 years ago
- Multiplicative Normalizing Flow (MNF) posteriors for variational Bayesian neural networks☆65Updated 4 years ago
- A variational inference method with accurate uncertainty estimation. It uses a new semi-implicit variational family built on neural netwo…☆53Updated 5 months ago
- Reliable Uncertainty Estimates in Deep Neural Networks using Noise Contrastive Priors☆62Updated 4 years ago