Details
Monte Carlo Gradient Estimators and Variational Inference
|
First, I’d like to say that I thoroughly enjoyed the the Advances in Approximate Bayesian Inference workshop at NIPS 2016 — great job Dustin Tran et al. An awesome poster (with a memorable name) from Geoffrey Roeder, Yuhai Wu, and David Duvenaud probed an important, but typically undiscussed choice that practitioners have to make when doing black-box variational inference with the pathwise gradient estimators1. This post describes the phenomenon that they point out. I will try to provide some additional intuition through wordy prose and a numerical experiment on a simple example. |
Submitted by elementlist on Dec 21, 2016 |
347 views. Averaging 0 views per day. |
Please login or register if you wish to leave a comment.
Submit
New Links
Most Popular
Quick Search
Statistics
3,012 listings in 21 categories, with 2,257,141 clicks. Directory last updated Sep 12, 2023.
Welcome Amara Fatima, the newest member.
Comments on Monte Carlo Gradient Estimators and Variational Inference