ACCELERATING EM BY TARGETED AGGRESSIVE DOUBLE EXTRAPOLATION

被引：0

作者：

Huang, Han-Shen ^{[1
]}

Yang, Bo-Hou ^{[1
,2
]}

Lyu, Ren-Yuan ^{[2
]}

Hsu, Chun-Nan ^{[1
]}

机构：

[1] Acad Sinica, Inst Informat Sci, Taipei, Taiwan

[2] Chang Gung Univ, Dept Elect Engn, Taoyuan, Taiwan

来源：

2009 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1- 8, PROCEEDINGS | 2009年

关键词：

Eigenvalues and eigenfunctions; Parameter estimation; Extrapolation; Convergence of numerical methods; Acceleration; ALGORITHM;

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

The Expectation-Maximization (EM) algorithm is one of the most popular algorithms for parameter estimation from incomplete data, but its convergence can be slow for some large-scale or complex problems. Extrapolation methods can effectively accelerate EM, but to ensure stability, the learning rate of extrapolation must be compromised. This paper describes the TJ(2) aEM method, a targeted extrapolation method that can extrapolate much more aggressively than competing methods without causing instability problems. We analyze its convergence properties and report experimental results.

引用

页码：1609 / +

页数：2

共 50 条

[1] Quadratic extrapolation for accelerating convergence of the EM fixed point problem
Saadaoui, Foued
[J]. JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS, 2020, 369
[2] Randomized extrapolation for accelerating EM-type fixed-point algorithms
Saadaoui, Foued
[J]. JOURNAL OF MULTIVARIATE ANALYSIS, 2023, 196
[3] Global and componentwise extrapolation for accelerating data mining from large incomplete data sets with the EM algorithm
Hsu, Chun-Nan
Huang, Han-Shen
Yang, Bo-Hou
[J]. ICDM 2006: SIXTH INTERNATIONAL CONFERENCE ON DATA MINING, PROCEEDINGS, 2006, : 265 - +
[4] Accelerating distributed consensus using extrapolation
Kokiopoulou, Effrosyni
Frossard, Pascal
[J]. IEEE SIGNAL PROCESSING LETTERS, 2007, 14 (10) : 665 - 668
[5] Accelerating EM for large databases
Thiesson, B
Meek, C
Heckerman, D
[J]. MACHINE LEARNING, 2001, 45 (03) : 279 - 299
[6] Accelerating EM for Large Databases
Bo Thiesson
Christopher Meek
David Heckerman
[J]. Machine Learning, 2001, 45 : 279 - 299
[7] Accelerating EM: An empirical study
Ortiz, LE
Kaelbling, LP
[J]. UNCERTAINTY IN ARTIFICIAL INTELLIGENCE, PROCEEDINGS, 1999, : 512 - 521
[8] Measures. for accelerating EM computations
Baghai-Wadji, AR
[J]. MATHEMATICAL METHODS IN ELECTROMAGNETIC THEORY, CONFERENCE PROCEEDINGS, VOLS 1 AND 2, 2002, : 27 - 32
[9] Accelerating Nonnegative Matrix Factorization Algorithms Using Extrapolation
Ang, Andersen Man Shun
Gillis, Nicolas
[J]. NEURAL COMPUTATION, 2019, 31 (02) : 417 - 439
[10] ACCELERATING WAVEFIELD EXTRAPOLATION ISOCHRON-RAY MIGRATION
Ferreira Da Silva, Eduardo Filpo
Sava, Paul
[J]. JOURNAL OF SEISMIC EXPLORATION, 2009, 18 (01): : 21 - 41

← 1 2 3 4 5 →