flaviomorelli / vi_gentle_introduction

Variational inference is a technique for estimating Bayesian models that provides similar precision to MCMC at a greater speed, and is one of the main areas of current research in Bayesian computation. In this introductory talk, we take a look at the theory behind the variational approach and some of the most common methods (e.g. mean field, stochastic, black box). The focus of this talk is the intuition behind variational inference, rather than the mathematical details of the methods. At the end of this talk, you will have a basic grasp of variational Bayes and its limitations.

Variational Bayes: A Gentle Introduction

This repository contains the Jupyter Notebook for the talk Variational Bayes: A Gentle Introduction

The notebook on variational inference with PyMC3 is based on this blogpost

The slides for the talk can be found here