- This repository contains the notebook files implementation for Pyro tutorial. Official Pyro tutorial here: Official Tutorial
- Pyro is a universal probabilistic programming language (PPL) written in Python and supported by PyTorch on the backend. Pyro enables flexible and expressive deep probabilistic modeling, unifying the best of modern deep learning and Bayesian modeling. It was designed with these key principles:
- Universal: Pyro can represent any computable probability distribution.
- Scalable: Pyro scales to large data sets with little overhead.
- Minimal: Pyro is implemented with a small core of powerful, composable abstractions.
- Flexible: Pyro aims for automation when you want it, control when you need it.
- An Introduction to Models and Inference in Pyro
- SVI part I: An Introduction to Stochastic Variational Inference in Pyro
- Mini Pyro explanation/implementation with some examples
- Variational Autoencoder
- Poutine: A Guide to Programming with Effect Handlers(and some tensor shape intro)
- Gaussian Mixture Model
- Hard Coding Normalizing Flow implementation without Pyro
- Gaussian Mixture Model Modification with some other AutoGuide tools
- VAE notebook for text matching and the original implementation github can be found here for DeConvolutionVAE
- Bayesian Canonical Correlation Analysis implementation in PyTorch + Tensor shape/torch.constraints/Simple examples review
- Bayesian Regression + VAE tutorial + BCCA estimation via Normalizing Flows
- Flows + BCCA: initial attempt to combine a sequence of transformations and BCCA model