On the uniqueness of loopy belief propagation fixed points

被引:67
|
作者
Heskes, T [1 ]
机构
[1] Univ Nijmegen, SNN, NL-6525 EZ Nijmegen, Netherlands
关键词
D O I
10.1162/0899766041941943
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We derive sufficient conditions for the uniqueness of loopy belief propagation fixed points. These conditions depend on both the structure of the graph and the strength of the potentials and naturally extend those for convexity of the Bethe free energy. We compare them with (a strengthened version of) conditions derived elsewhere for pairwise potentials. We discuss possible implications for convergent algorithms, as well as for other approximate free energies.
引用
收藏
页码:2379 / 2413
页数:35
相关论文
共 50 条
  • [21] On Sentiment Polarity Assignment in the Wordnet Using Loopy Belief Propagation
    Kulisiewicz, Marcin
    Kajdanowicz, Tomasz
    Kazienko, Przemyslaw
    Piasecki, Maciej
    HYBRID ARTIFICIAL INTELLIGENT SYSTEMS (HAIS 2015), 2015, 9121 : 451 - 462
  • [23] On the convergence of loopy belief propagation algorithm for different update rules
    Taga, N
    Mase, S
    IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2006, E89A (02) : 575 - 582
  • [24] An Analysis into the Loopy Belief Propagation Algorithm over Short Cycles
    Raveendran, Nithin
    Srinivasa, Shayan Garani
    2014 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC), 2014, : 2009 - 2014
  • [25] Learning multiple belief propagation fixed points for real time inference
    Furtlehner, Cyril
    Lasgouttes, Jean-Marc
    Auger, Anne
    PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, 2010, 389 (01) : 149 - 163
  • [26] Loopy Belief Propagation Application for Advanced Decision Making Models
    Watthayu, Wiboonsak
    PROCEEDINGS OF THE 2ND INTERNATIONAL SYMPOSIUM ON COMPUTER, COMMUNICATION, CONTROL AND AUTOMATION, 2013, 68 : 213 - 216
  • [27] Applications of Gibbs measure theory to loopy belief propagation algorithm
    Taga, Nobuyuki
    Mase, Shigeru
    MICAI 2006: ADVANCES IN ARTIFICIAL INTELLIGENCE, PROCEEDINGS, 2006, 4293 : 197 - +
  • [28] Dense motion and disparity estimation via loopy belief propagation
    Isard, M
    MacCormick, J
    COMPUTER VISION - ACCV 2006, PT II, 2006, 3852 : 32 - 41
  • [29] On the properties of the Bethe approximation and loopy belief propagation on binary networks
    Mooij, JM
    Kappen, HJ
    JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT, 2005, : 231 - 248
  • [30] Bayesian Image Segmentations by Potts Prior and Loopy Belief Propagation
    Tanaka, Kazuyuki
    Kataoka, Shun
    Yasuda, Muneki
    Waizumi, Yuji
    Hsu, Chiou-Ting
    JOURNAL OF THE PHYSICAL SOCIETY OF JAPAN, 2014, 83 (12)