BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Monte Carlo Gradient Estimation in Machine Learning - James Alling
 ham (University of Cambridge)
DTSTART:20210407T100000Z
DTEND:20210407T113000Z
UID:TALK157387@talks.cam.ac.uk
CONTACT:Elre Oldewage
DESCRIPTION:In this talk\, I'll go over the (semi-)recent review paper for
  Monte Carlo gradient estimation methods in machine learning (Mohammed et 
 al.\, 2019). This work discusses the problem of estimating the gradient of
  an expectation. This problem comes up regularly in machine learning\, for
  example\, in variational inference and reinforcement learning. The paper 
 looks at three different methods for solving the problem: the pathwise\, s
 core function\, and measure-valued gradient estimators. In addition to des
 cribing the gradient estimation problem\, I'll describe each of these esti
 mators\, their properties\, and some advice for choosing one in practice. 
 \n\nRequired reading: None. This talk is aimed at people without intimate 
 knowledge of Monte-Carlo gradient estimators and should be easy to follow 
 for anyone with a general machine learning background. However\, those int
 erested could skim sections 1 and 2 of Mohammed et al. (2019) for an intro
 duction to the problem.\n\nShakir Mohamed\, Mihaela Rosca\, Michael Figurn
 ov\, Andriy Mnih: Monte Carlo Gradient Estimation in Machine Learning. J. 
 Mach. Learn. Res. 21: 132:1-132:62 (2020)\, https://arxiv.org/abs/1906.106
 52 
LOCATION:https://eng-cam.zoom.us/j/82019956685?pwd=WUNSVVcrdC9IZGxQOHFhSTh
 jUjd2dz09
END:VEVENT
END:VCALENDAR