A Gradient-Based Algorithm Competitive with Variational Bayesian EM for Mixture of Gaussians

被引:0
|
作者
Kuusela, Mikael [1 ]
Raiko, Tapani [1 ]
Honkela, Antti [1 ]
Karhunen, Juha [1 ]
机构
[1] Aalto Univ, Adapt Informat Res Ctr, Helsinki, Finland
关键词
CONJUGATE-GRADIENT;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
While variational Bayesian (VB) inference is typically done with the so called VB EM algorithm, there are models where it cannot be applied because either the E-step or the M-step cannot be solved analytically. In 2007, Honkela et al. introduced a recipe for a gradient-based algorithm for VB inference that does not have such a restriction. In this paper, we derive the algorithm in the case of the mixture of Gaussians model. For the first time, the algorithm is experimentally compared to VB EM and its variant with both artificial and real data. We conclude that the algorithms are approximately as fast depending on the problem.
引用
收藏
页码:1011 / 1018
页数:8
相关论文
共 50 条
  • [41] Time/order update gradient-based adaptive algorithm
    Mayyas, K
    Aboulnasr, T
    [J]. ISSPA 96 - FOURTH INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND ITS APPLICATIONS, PROCEEDINGS, VOLS 1 AND 2, 1996, : 296 - 299
  • [42] Iris Recognition on Images Reconstructed with Gradient-based Algorithm
    Radojicic, Tijana
    Bozovic, Milena
    Blagojevic, Nina
    [J]. 2020 9TH MEDITERRANEAN CONFERENCE ON EMBEDDED COMPUTING (MECO), 2020, : 384 - 387
  • [43] Algorithm 1035: A Gradient-based Implementation of the Polyhedral Active Set Algorithm
    Hager, William W.
    Zhang, Hongchao
    [J]. ACM TRANSACTIONS ON MATHEMATICAL SOFTWARE, 2023, 49 (02):
  • [44] Genetic Algorithm and Gradient-based Algorithm Optimization of Vehicle Turning Mechanism
    Song, Yandong
    Xi, Pingyuan
    [J]. 2009 2ND IEEE INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND INFORMATION TECHNOLOGY, VOL 3, 2009, : 81 - +
  • [45] Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm
    Liu, Qiang
    Wang, Dilin
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 29 (NIPS 2016), 2016, 29
  • [46] A Modified Stein Variational Inference Algorithm with Bayesian and Gradient Descent Techniques
    Zhang, Limin
    Dong, Jing
    Zhang, Junfang
    Yang, Junzi
    [J]. SYMMETRY-BASEL, 2022, 14 (06):
  • [47] UNBIASED MLMC STOCHASTIC GRADIENT-BASED OPTIMIZATION OF BAYESIAN EXPERIMENTAL DESIGNS
    Goda, Takashi
    Hironaka, Tomohiko
    Kitade, Wataru
    Foster, Adam
    [J]. SIAM JOURNAL ON SCIENTIFIC COMPUTING, 2022, 44 (01): : A286 - A311
  • [48] Mutant Altimetric Parameter Estimation Using a Gradient-Based Bayesian Method
    Liao, Xianghong
    Zhang, Zenghui
    Jiang, Ge
    [J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
  • [49] Stochastic Gradient-Based Distributed Bayesian Estimation in Cooperative Sensor Networks
    Cadena, Jose
    Ray, Priyadip
    Chen, Hao
    Soper, Braden
    Rajan, Deepak
    Yen, Anton
    Goldhahn, Ryan
    [J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2021, 69 (69) : 1713 - 1724
  • [50] Revisiting Skipped Filter and Development of Robust Localization Method Based on Variational Bayesian Gaussian Mixture Algorithm
    Park, Chee-Hyun
    Chang, Joon-Hyuk
    [J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2022, 70 : 5639 - 5651