amirgholami / PyHessian
PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks
☆726Updated 11 months ago
Alternatives and similar repositories for PyHessian:
Users that are interested in PyHessian are comparing it to the libraries listed below
- Efficient PyTorch Hessian eigendecomposition tools!☆370Updated last year
- ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning☆271Updated 2 years ago
- BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.☆573Updated 2 months ago
- Approximating neural network loss landscapes in low-dimensional parameter subspaces for PyTorch☆323Updated last year
- Mode Connectivity and Fast Geometric Ensembles in PyTorch☆268Updated 2 years ago
- {KFAC,EKFAC,Diagonal,Implicit} Fisher Matrices and finite width NTKs in PyTorch☆211Updated last week
- A repository in preparation for open-sourcing lottery ticket hypothesis code.☆629Updated 2 years ago
- hessian in pytorch☆187Updated 4 years ago
- ☆588Updated 4 months ago
- ☆224Updated 7 months ago
- PyTorch library to facilitate development and standardized evaluation of neural network pruning methods.☆428Updated last year
- ASDL: Automatic Second-order Differentiation Library for PyTorch☆185Updated 3 months ago
- ☆188Updated 4 years ago
- Open-source code for paper "Dataset Distillation"☆792Updated 2 years ago
- Laplace approximations for Deep Learning.☆498Updated last month
- A general and accurate MACs / FLOPs profiler for PyTorch models☆601Updated 10 months ago
- ☆157Updated 2 years ago
- Code for experiments in my blog post on the Neural Tangent Kernel: https://eigentales.com/NTK☆172Updated 5 years ago
- A PyTorch implementation of L-BFGS.☆598Updated 2 years ago
- functorch is JAX-like composable function transforms for PyTorch.☆1,416Updated this week
- This repository contains a Pytorch implementation of the paper "The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks"…☆330Updated last year
- Reproduce CKA: Similarity of Neural Network Representations Revisited☆298Updated 4 years ago
- Create animations for the optimization trajectory of neural nets☆147Updated last year
- Compare neural networks by their feature similarity☆354Updated last year
- Estimate/count FLOPS for a given neural network using pytorch☆303Updated 2 years ago
- Code for Neural Architecture Search without Training (ICML 2021)☆465Updated 3 years ago
- ☆202Updated 2 years ago
- A LARS implementation in PyTorch☆343Updated 5 years ago
- Hessian spectral density estimation in TF and Jax☆122Updated 4 years ago
- End-to-end training of sparse deep neural networks with little-to-no performance loss.☆319Updated 2 years ago