Comparison of Gradient Descent Methods in Online Fuzzy Co-clustering

被引:0
作者
Kida, Keiko [1 ]
Ubukata, Seiki [1 ]
Notsu, Akira [2 ]
Honda, Katsuhiro [1 ]
机构
[1] Osaka Prefecture Univ, Grad Sch Engn, Sakai, Osaka 5998531, Japan
[2] Osaka Prefecture Univ, Grad Sch Humanities & Sustainable Syst Sci, Sakai, Osaka 5998531, Japan
来源
2019 INTERNATIONAL CONFERENCE ON FUZZY THEORY AND ITS APPLICATIONS (IFUZZY) | 2019年
关键词
Fuzzy co-clustering; FCCMM; Online algorithm; gradient descent method;
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
Fuzzy co-clustering schemes including Fuzzy Co-Clustering induced by Multinomial Mixture models (FCCMM) are promising approaches for analyzing object-item cooccurrence information such as document-keyword frequencies and customer-product purchase history transactions. However, such cooccurrence datasets are generally maintained as very large matrices and cannot be dealt with conventional batch algorithms. In order to deal with such problems, online FCCMM (OFCCMM) that sequentially loads a single object has been proposed. Conventional OFCCMM uses stochastic gradient descent (SGD) to update parameters. SGD generally has drawbacks that convergence is slow and it is susceptible to vibration state and a saddle point. Many improvements on SGD have been proposed such as Momentum SGD, Nesterov's accelerated gradient method, AdaGrad, and Adam. In this study, we introduce various gradient descent methods into OFCCMM and observe their characteristics and performance through numerical experiments.
引用
收藏
页码:9 / 14
页数:6
相关论文
共 47 条
[41]   Image Alignment by Online Robust PCA via Stochastic Gradient Descent [J].
Song, Wenjie ;
Zhu, Jianke ;
Li, Yang ;
Chen, Chun .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2016, 26 (07) :1241-1250
[42]   Designing fuzzy inference system based on improved gradient descent method [J].
Zhang Liquan Shao Cheng Research Center of Information and Control Dalian Univ of Technology Dalian P R China .
JournalofSystemsEngineeringandElectronics, 2006, (04) :853-857+863
[43]   Ionospheric forecasting model using fuzzy logic-based gradient descent method [J].
D.Venkata Ratnam ;
G.Vindhya ;
J.R.K.Kumar Dabbakuti .
Geodesy and Geodynamics, 2017, (05) :305-310
[44]   Extremum seeking of dynamical systems via gradient descent and stochastic approximation methods [J].
Khong, Sei Zhen ;
Tan, Ying ;
Manzie, Chris ;
Nesic, Dragan .
AUTOMATICA, 2015, 56 :44-52
[45]   Gradient descent-based parameter-free methods for solving coupled matrix equations and studying an application in dynamical systems [J].
Shirilord, Akbar ;
Dehghan, Mehdi .
APPLIED NUMERICAL MATHEMATICS, 2025, 212 :29-59
[46]   Particle Swarm Optimization and Gradient Descent Methods for Optimization of PI Controller for AGC of Multi-area Thermal-Wind-Hydro Power Plants [J].
Kumari, Naresh ;
Jha, A. N. .
UKSIM-AMSS 15TH INTERNATIONAL CONFERENCE ON COMPUTER MODELLING AND SIMULATION (UKSIM 2013), 2013, :536-541
[47]   Modeling of first order plus time delay system dynamics with adaptive IIR filters based on gradient descent methods and performance analyses for different time delay cases [J].
Yagmur, Nagihan ;
Alagoz, Baris Baykant .
PAMUKKALE UNIVERSITY JOURNAL OF ENGINEERING SCIENCES-PAMUKKALE UNIVERSITESI MUHENDISLIK BILIMLERI DERGISI, 2024, 30 (02) :202-211