Hessian spectral density estimation in TF and Jax
☆125Sep 6, 2020Updated 6 years ago
Alternatives and similar repositories for spectral-density
Users that are interested in spectral-density are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians (ICML 2019)☆15Apr 27, 2019Updated 7 years ago
- The Full Spectrum of Deepnet Hessians at Scale: Dynamics with SGD Training and Sample Size☆19May 19, 2019Updated 7 years ago
- Efficient PyTorch Hessian eigendecomposition tools!☆475Oct 23, 2026Updated last week
- PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks☆795Jul 10, 2025Updated last year
- ☆32Feb 11, 2021Updated 5 years ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- ☆85Jan 15, 2020Updated 6 years ago
- Fast and Easy Infinite Neural Networks in Python☆2,386Mar 1, 2024Updated 2 years ago
- ☆12Oct 8, 2020Updated 6 years ago
- Public Codebase for Rethinking Parameter Counting: Effective Dimensionality Revisited☆37Dec 27, 2022Updated 3 years ago
- Probabilistic Solution of Differential Equations☆13Jun 19, 2022Updated 4 years ago
- Second Order Optimization and Curvature Estimation with K-FAC in JAX.☆332Oct 13, 2026Updated 2 weeks ago
- can calculate the Hessian matrix and/or its spectrum for simple neural nets☆11May 7, 2018Updated 8 years ago
- ☆80Sep 4, 2021Updated 5 years ago
- Matlab code implementing Minimum Probability Flow Learning.☆69Sep 17, 2014Updated 12 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- MDL Complexity computations and experiments from the paper "Revisiting complexity and the bias-variance tradeoff".☆18Jun 12, 2023Updated 3 years ago
- ☆16Jun 3, 2025Updated last year
- codebase for "A Theory of the Inductive Bias and Generalization of Kernel Regression and Wide Neural Networks"☆52May 2, 2023Updated 3 years ago
- Path Tracing in JAX☆74Dec 15, 2019Updated 6 years ago
- BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.☆619Jul 17, 2026Updated 3 months ago
- Pytorch implementation of KFAC and E-KFAC (Natural Gradient).☆135Jul 2, 2019Updated 7 years ago
- ☆100Dec 8, 2021Updated 4 years ago
- [ICML'21 Oral] Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding☆14Jun 10, 2021Updated 5 years ago
- Hessian trace estimation using PyTorch and Hutch++☆20Oct 29, 2020Updated 6 years ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- ☆332Sep 20, 2022Updated 4 years ago
- An example showing how to use jax to train resnet50 on multi-node multi-GPU☆20Jul 4, 2022Updated 4 years ago
- This repository contains the code used in a publication 'Active Learning for Decision-Making from Imbalanced Observational Data', Iiris S…☆11May 14, 2019Updated 7 years ago
- ☆42Nov 9, 2019Updated 6 years ago
- Lightweight library of stochastic gradient MCMC algorithms written in JAX.☆106Oct 23, 2023Updated 3 years ago
- Energy-Aware Neural Architecture Optimization with Fast Splitting Steepest Descent☆14Feb 6, 2020Updated 6 years ago
- {KFAC,EKFAC,Diagonal,Implicit} Fisher Matrices and finite width NTKs in PyTorch☆225Oct 13, 2026Updated 2 weeks ago
- Flexible, general-purpose VMC framework, built on JAX.☆33Aug 23, 2026Updated 2 months ago
- ☆646Jul 24, 2026Updated 3 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Hardware accelerated, batchable and differentiable optimizers in JAX.☆1,067Oct 16, 2026Updated 2 weeks ago
- Mathematical operations for JAX pytrees☆209Dec 5, 2024Updated last year
- We define and estimate smooth unique information of samples with respect to classifier weights and predictions. We compute these quantiti…☆11Mar 9, 2021Updated 5 years ago
- Code release for the ICLR paper☆22Jun 13, 2018Updated 8 years ago
- Forward mode laplacian implemented in JAX tracer☆32Jan 7, 2026Updated 9 months ago
- PyTorch AutoNEB implementation to identify minimum energy paths, e.g. in neural network loss landscapes☆57Sep 14, 2022Updated 4 years ago
- Sampled Quasi-Newton Methods for Deep Learning☆21May 21, 2020Updated 6 years ago