University of Cambridge > Talks.cam > Machine Learning Reading Group @ CUED > Monte Carlo Gradient Estimation in Machine Learning

Monte Carlo Gradient Estimation in Machine Learning

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Elre Oldewage.

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, score function, and measure-valued gradient estimators. In addition to describing the gradient estimation problem, I’ll describe each of these estimators, their properties, and some advice for choosing one in practice.

Required 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 interested could skim sections 1 and 2 of Mohammed et al. (2019) for an introduction to the problem.

Shakir Mohamed, Mihaela Rosca, Michael Figurnov, Andriy Mnih: Monte Carlo Gradient Estimation in Machine Learning. J. Mach. Learn. Res. 21: 132:1-132:62 (2020), https://arxiv.org/abs/1906.10652

This talk is part of the Machine Learning Reading Group @ CUED series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2021 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity