✳flâneur — a map of the web's best reading
Eric Jang: A Beginner's Guide to Variational Methods: Mean-Field Approximation
blog.evjang.com · 2,900 words · saved by 1 readers
Variational Bayeisan (VB) Methods are a family of techniques that are very popular in statistical Machine Learning. VB methods allow us to r...
Eric Jang: A Beginner's Guide to Variational Methods: Mean-Field Approximation Sunday, August 7, 2016 A Beginner's Guide to Variational Methods: Mean-Field Approximation Variational Bayeisan (VB) Methods are a family of techniques that are very popular in statistical Machine Learning. VB methods allow us to re-write statistical inference problems (i.e. infer the value of a random variable given the value of another random variable) as optimization problems (i.e. find the parameter values that minimize some objective function). This inference-optimization duality is powerful because it allows u
Explore this link on the map →related reading
- Mediumandacdemir-94699.medium.com
- Approximating KL Divergencejoschu.net
- Tutorial - What is a variational autoencoder? – Jaan Lı 李jaan.io
- Andy Jonesandrewcharlesjones.github.io
- Bayesian Neural Networkscs.toronto.edu
- blog.alexalemi.com KL is All You Needblog.alexalemi.com
- Six (and a half) intuitions for KL divergence — LessWronglesswrong.com
- Variational Inference with Normalizing Flowsarxiv.org
- The Reparameterization Trickgregorygundersen.com
- Kullback–Leibler divergence - Wikipediaen.wikipedia.org
- Variational autoencoder - Wikipediaen.wikipedia.org
- Exponential families from a single KL identityarxiv.org