Gumbel Mathemagic

Abstract

Those who have seen the talk “Stochastic Beams and Where to Find Them” can tune in 20 mins late as I will explain to you the mathemagic behind Stochastic Beam Search, an extension of the Gumbel-Max trick that enables sampling sequences without replacement. After that I will discuss Ancestral-Gumbel-Top-k Sampling, which is a generalization of Stochastic Beam Search. Finally, I will derive a multi-sample REINFORCE estimator with built-in baseline, based on sampling without replacement. All made possible by the humble Gumbel! 🙂 Bring your own snacks!

Date
Location
Online
Avatar
Wouter Kool
Machine Learning & Optimization

Scientist & engineer with a PhD in machine learning and a passion for (combinatorial) optimization.