gknilsen / pyhessian
pyhessian is a TensorFlow module which can be used to estimate Hessian matrices
☆24Updated 4 years ago
Alternatives and similar repositories for pyhessian:
Users that are interested in pyhessian are comparing it to the libraries listed below
- Collection of algorithms for approximating Fisher Information Matrix for Natural Gradient (and second order method in general)☆139Updated 5 years ago
- Limitations of the Empirical Fisher Approximation☆47Updated 2 months ago
- Geometric Certifications of Neural Nets☆41Updated 2 years ago
- This repository contains the Julia code for the paper "Competitive Gradient Descent"☆24Updated 5 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
- paper lists and information on mean-field theory of deep learning☆74Updated 6 years ago
- Minimax Optimization, Stackelberg Games, Generative Adversarial Networks☆19Updated 5 years ago
- Sample code for running deterministic variational inference to train Bayesian neural networks☆100Updated 6 years ago
- Computing various norms/measures on over-parametrized neural networks☆49Updated 6 years ago
- Hypergradient descent☆146Updated 11 months ago
- NTK reading group☆88Updated 5 years ago
- Convolutional Neural Tangent Kernel☆111Updated 5 years ago
- ☆26Updated 6 years ago
- PyTorch implementation of FIM and empirical FIM☆60Updated 6 years ago
- Approximate Inference Turns Deep Networks into Gaussian Processes (dnn2gp)☆48Updated 5 years ago
- ☆166Updated 9 months ago
- Repository containing Pytorch code for EKFAC and K-FAC perconditioners.☆142Updated last year
- ☆29Updated 4 years ago
- PyTorch implementation of Hessian Free optimisation☆43Updated 5 years ago
- Natural Gradient, Variational Inference☆29Updated 5 years ago
- PyTorch-SSO: Scalable Second-Order methods in PyTorch☆145Updated last year
- Visualizing the the loss landscape of Fully-Connected Neural Networks☆45Updated last year
- The Full Spectrum of Deepnet Hessians at Scale: Dynamics with SGD Training and Sample Size☆17Updated 5 years ago
- Certifying Some Distributional Robustness with Principled Adversarial Training (https://arxiv.org/abs/1710.10571)☆45Updated 7 years ago
- Code for "A Spectral Approach to Gradient Estimation for Implicit Distributions" (ICML'18)☆33Updated last year
- Regularization, Neural Network Training Dynamics☆14Updated 5 years ago
- Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians (ICML 2019)☆17Updated 6 years ago
- Randomized Smoothing of All Shapes and Sizes (ICML 2020).☆52Updated 4 years ago
- Monotone operator equilibrium networks☆51Updated 4 years ago
- Computing the eigenvalues of Neural Tangent Kernel and Conjugate Kernel (aka NNGP kernel) over the boolean cube☆47Updated 5 years ago