Preprint Article Version 4 Preserved in Portico This version is not peer-reviewed

Tutorial on EM Algorithm

Version 1 : Received: 17 February 2018 / Approved: 20 February 2018 / Online: 20 February 2018 (15:37:19 CET)
Version 2 : Received: 22 February 2018 / Approved: 22 February 2018 / Online: 22 February 2018 (16:28:05 CET)
Version 3 : Received: 27 February 2018 / Approved: 27 February 2018 / Online: 27 February 2018 (15:06:35 CET)
Version 4 : Received: 8 September 2020 / Approved: 14 September 2020 / Online: 14 September 2020 (07:28:46 CEST)
Version 5 : Received: 22 September 2020 / Approved: 23 September 2020 / Online: 23 September 2020 (04:35:28 CEST)

How to cite: Nguyen, L. Tutorial on EM Algorithm. Preprints 2018, 2018020131 (doi: 10.20944/preprints201802.0131.v4). Nguyen, L. Tutorial on EM Algorithm. Preprints 2018, 2018020131 (doi: 10.20944/preprints201802.0131.v4).

Abstract

Maximum likelihood estimation (MLE) is a popular method for parameter estimation in both applied probability and statistics but MLE cannot solve the problem of incomplete data or hidden data because it is impossible to maximize likelihood function from hidden data. Expectation maximum (EM) algorithm is a powerful mathematical tool for solving this problem if there is a relationship between hidden data and observed data. Such hinting relationship is specified by a mapping from hidden data to observed data or by a joint probability between hidden data and observed data. In other words, the relationship helps us know hidden data by surveying observed data. The essential ideology of EM is to maximize the expectation of likelihood function over observed data based on the hinting relationship instead of maximizing directly the likelihood function of hidden data. Pioneers in EM algorithm proved its convergence. As a result, EM algorithm produces parameter estimators as well as MLE does. This tutorial aims to provide explanations of EM algorithm in order to help researchers comprehend it. Moreover some improvements of EM algorithm are also proposed in the tutorial such as combination of EM and third-order convergence Newton-Raphson process, combination of EM and gradient descent method, and combination of EM and particle swarm optimization (PSO) algorithm.

Subject Areas

expectation maximum; EM; generalized expectation maximum; GEM; EM convergence

Comments (1)

Comment 1
Received: 14 September 2020
Commenter: Loc Nguyen
Commenter's Conflict of Interests: Author
Comment: There are two major changes as follows:
1. Computing the conditional expectation Q for data sample (pages 12 - 14).
2. Adding section 5.1 about mixture model with EM algorithm.
However, some bugs related to logic and paper structure are fixed.
+ Respond to this comment

We encourage comments and feedback from a broad range of readers. See criteria for comments and our diversity statement.

Leave a public comment
Send a private comment to the author(s)
Views 0
Downloads 0
Comments 1
Metrics 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here.