gknilsen / pyhessianLinks
pyhessian is a TensorFlow module which can be used to estimate Hessian matrices
☆25Updated 4 years ago
Alternatives and similar repositories for pyhessian
Users that are interested in pyhessian are comparing it to the libraries listed below
Sorting:
- Collection of algorithms for approximating Fisher Information Matrix for Natural Gradient (and second order method in general)☆142Updated 6 years ago
- Repository containing Pytorch code for EKFAC and K-FAC perconditioners.☆149Updated 2 years ago
- Hessian spectral density estimation in TF and Jax☆124Updated 5 years ago
- Convolutional Neural Tangent Kernel☆112Updated 6 years ago
- paper lists and information on mean-field theory of deep learning☆78Updated 6 years ago
- Geometric Certifications of Neural Nets☆42Updated 3 years ago
- Hypergradient descent☆147Updated last year
- Limitations of the Empirical Fisher Approximation☆49Updated 9 months ago
- NTK reading group☆87Updated 6 years ago
- ☆126Updated last year
- This repository contains a simple implementation of Interval Bound Propagation (IBP) using TensorFlow: https://arxiv.org/abs/1810.12715☆161Updated 6 years ago
- Contains code for the NeurIPS 2020 paper by Pan et al., "Continual Deep Learning by FunctionalRegularisation of Memorable Past"☆44Updated 5 years ago
- PyTorch-SSO: Scalable Second-Order methods in PyTorch☆148Updated 2 years ago
- ☆157Updated 3 years ago
- Minimax Optimization, Stackelberg Games, Generative Adversarial Networks☆19Updated 5 years ago
- PyTorch implementation of FIM and empirical FIM☆60Updated 7 years ago
- ☆68Updated 6 years ago
- This repository contains the Julia code for the paper "Competitive Gradient Descent"☆25Updated 6 years ago
- ☆155Updated 5 years ago
- ☆172Updated last year
- Approximate Inference Turns Deep Networks into Gaussian Processes (dnn2gp)☆48Updated 6 years ago
- Pytorch implementation of KFAC and E-KFAC (Natural Gradient).☆132Updated 6 years ago
- Sample code for running deterministic variational inference to train Bayesian neural networks☆101Updated 7 years ago
- Code for the paper: "Tensor Programs II: Neural Tangent Kernel for Any Architecture"☆106Updated 5 years ago
- Monotone operator equilibrium networks☆54Updated 5 years ago
- Certifying Some Distributional Robustness with Principled Adversarial Training (https://arxiv.org/abs/1710.10571)☆45Updated 7 years ago
- hessian in pytorch☆187Updated 5 years ago
- Visualizing the the loss landscape of Fully-Connected Neural Networks☆46Updated 2 years ago
- CHOP: An optimization library based on PyTorch, with applications to adversarial examples and structured neural network training.☆78Updated last year
- Experiments for the paper "Exponential expressivity in deep neural networks through transient chaos"☆74Updated 9 years ago