Semi-supervised logistic discrimination via labeled data and unlabeled data from different sampling distributions

DOI10.1002/SAM.11204zbMATH Open1281.62148arXiv1108.5244OpenAlexW2949866066MaRDI QIDQ2870752FDOQ2870752

Shuichi Kawano

Publication date: 21 January 2014

Published in: Statistical Analysis and Data Mining (Search for Journal in Brave)

Abstract: This article addresses the problem of classification method based on both labeled and unlabeled data, where we assume that a density function for labeled data is different from that for unlabeled data. We propose a semi-supervised logistic regression model for classification problem along with the technique of covariate shift adaptation. Unknown parameters involved in proposed models are estimated by regularization with EM algorithm. A crucial issue in the modeling process is the choices of tuning parameters in our semi-supervised logistic models. In order to select the parameters, a model selection criterion is derived from an information-theoretic approach. Some numerical studies show that our modeling procedure performs well in various cases.

Full work available at URL: https://arxiv.org/abs/1108.5244

Recommendations

• Semi-supervised logistic discrimination via regularized Gaussian basis expansions
• Semi-supervised logistic discrimination for functional data
• On semi-supervised linear regression in covariate shift problems
• Semi-supervised learning via constraints
• Semi-supervised learning with density-ratio estimation

zbMATH Keywords

model selectionEM algorithmregularizationsemi-supervised learningcovariate shifts

Mathematics Subject Classification ID

Statistical aspects of information-theoretic topics (62B10) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05) Generalized linear models (logistic models) (62J12)

Cites Work

• The use of unlabeled data in predictive modeling
• Using Unlabelled Data to Update Classification Rules with Applications in Food Authenticity Studies
• Title not available (Why is that?)
• Direct importance estimation for covariate shift adaptation
• Improving predictive inference under covariate shift by weighting the log-likelihood function
• Information and Posterior Probability Criteria for Model Selection in Local Likelihood Estimation
• Information criteria and statistical modeling.
• Generalised information criteria in model selection
• Nonlinear regression modeling via regularized radial basis function networks
• Bayesian factor analysis and information criterion
• A least-squares approach to direct importance estimation
• Discriminative learning under covariate shift
• Semi-supervised learning with density-ratio estimation
• Density ratio estimation in machine learning. Foreword by Thomas G. Dietterich
• Bayesian semi-supervised learning with support vector machine
• Title not available (Why is that?)
• Semi-Supervised Logistic Discrimination via Regularized Gaussian Basis Expansions
• Automatic bias correction methods in semi-supervised learning

Cited In (3)

• Machine Learning: ECML 2004
• Semi-supervised learning via constraints
• Classification from only positive and unlabeled functional data

This page was built for publication: Semi-supervised logistic discrimination via labeled data and unlabeled data from different sampling distributions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2870752)