Collection of algorithms for approximating Fisher Information Matrix for Natural Gradient (and second order method in general)
☆143May 26, 2019Updated 6 years ago
Alternatives and similar repositories for natural-gradients
Users that are interested in natural-gradients are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- {KFAC,EKFAC,Diagonal,Implicit} Fisher Matrices and finite width NTKs in PyTorch☆221Mar 31, 2026Updated 2 weeks ago
- Limitations of the Empirical Fisher Approximation☆49Mar 3, 2025Updated last year
- Repository containing Pytorch code for EKFAC and K-FAC perconditioners.☆153Jun 22, 2023Updated 2 years ago
- Code for "Accelerating Natural Gradient with Higher-Order Invariance"☆30Jun 28, 2019Updated 6 years ago
- Pytorch Implementation of paper "Noisy Natural Gradient as Variational Inference"☆122Sep 1, 2018Updated 7 years ago
- Serverless GPU API endpoints on Runpod - Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- TensorFlow implementation of "noisy K-FAC" and "noisy EK-FAC".☆60Jan 12, 2019Updated 7 years ago
- code for model-targeted poisoning☆12Oct 3, 2023Updated 2 years ago
- Pytorch implementation of KFAC and E-KFAC (Natural Gradient).☆134Jul 2, 2019Updated 6 years ago
- Example code for the NNGeometry PyTorch library☆10Aug 20, 2025Updated 7 months ago
- Model your data with the Von Mises-Fisher distribution in Python☆13Feb 1, 2016Updated 10 years ago
- Understanding Short-Horizon Bias in Stochastic Meta-Optimization☆37Mar 8, 2018Updated 8 years ago
- An implementation of KFAC for TensorFlow☆199Feb 11, 2022Updated 4 years ago
- Official Implementation of "Transferring Inductive Biases Through Knowledge Distillation"☆15Jun 3, 2020Updated 5 years ago
- Preconditioned Conjugate Gradient in Pytorch☆141Feb 14, 2024Updated 2 years ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- Code for "Differentiable Compositional Kernel Learning for Gaussian Processes" https://arxiv.org/abs/1806.04326☆71Jul 10, 2018Updated 7 years ago
- Pytorch implementation of KFAC - this is a port of https://github.com/tensorflow/kfac/☆31Jun 6, 2024Updated last year
- Official code for FAccT'21 paper "Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning" https://arxiv.org/abs…☆13Mar 9, 2021Updated 5 years ago
- Pytorch-based python library for continuous reinforcement learning and imitation learning [superseded by @osudrl/apex]☆13Mar 13, 2020Updated 6 years ago
- [ICML 2024] SINGD: KFAC-like Structured Inverse-Free Natural Gradient Descent (http://arxiv.org/abs/2312.05705)☆24Nov 4, 2024Updated last year
- Code for the paper: Why Transformers Need Adam: A Hessian Perspective☆65Mar 11, 2025Updated last year
- ☆11Nov 23, 2018Updated 7 years ago
- BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.☆611Nov 28, 2025Updated 4 months ago
- Efficient PyTorch Hessian eigendecomposition tools!☆385Feb 29, 2024Updated 2 years ago
- Wordpress hosting with auto-scaling - Free Trial • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Inverse Scaling in Test-Time Compute☆25Dec 3, 2025Updated 4 months ago
- Code for Knowledge-Adaptation Priors based on the NeurIPS 2021 paper by Khan and Swaroop.☆17Feb 1, 2022Updated 4 years ago
- Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians (ICML 2019)☆16Apr 27, 2019Updated 6 years ago
- PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks☆779Jul 10, 2025Updated 9 months ago
- Second Order Optimization and Curvature Estimation with K-FAC in JAX.☆319Updated this week
- IPython notebook with synthetic experiments for AFLite, based on the ICML 2020 paper, "Adversarial Filters of Dataset Biases".☆16Aug 14, 2020Updated 5 years ago
- ☆35Aug 30, 2021Updated 4 years ago
- Code for "EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis" https://arxiv.org/abs/1905.05934☆113Mar 3, 2020Updated 6 years ago
- Log to W&B from Julia☆12Jun 13, 2022Updated 3 years ago
- Wordpress hosting with auto-scaling - Free Trial • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- An extention to the GaLore paper, to perform Natural Gradient Descent in low rank subspace☆18Oct 21, 2024Updated last year
- Towards Understanding Sharpness-Aware Minimization [ICML 2022]☆38Jun 14, 2022Updated 3 years ago
- Computing various measures and generalization bounds on convolutional and fully connected networks☆35Dec 13, 2018Updated 7 years ago
- Pytorch optimizers implementing Hilbert Constrained Gradient Descent☆19May 9, 2019Updated 6 years ago
- Fast and Easy Infinite Neural Networks in Python☆2,380Mar 1, 2024Updated 2 years ago
- Implementation of the Deep Frank-Wolfe Algorithm -- Pytorch☆62Mar 6, 2021Updated 5 years ago
- This code reproduces the results of the paper, "Measuring Data Leakage in Machine-Learning Models with Fisher Information"☆48Aug 17, 2021Updated 4 years ago