Monte Carlo Sampling using Langevin Dynamics

April 17, 2020
Langevin Monte Carlo is a class of Markov Chain Monte Carlo algorithms that generate samples from a probability distribution of interest by simulating the Langevin Equation. This post explores the basics of Langevin Monte Carlo.
Read More

Normalizing Flows: Planar and Radial Flows

September 28, 2018
A normalizing flow is a great tool that can transform simple probability distributions into very complex ones by applying a series of invertible functions to samples from the simple distribution. This post explores two simple flows introduced by Rezende and Mohamed (2015) –– Planar Flow and Radial Flow.
Read More

Implicit Reparameterization Gradients

September 21, 2018
Backpropagation through a stochastic node is an important problem in deep learning. Implicit reparameterization gradients go beyond the reparameterization trick to address the problem of efficient gradient computation in such a setting.
Read More