スズキ　ジョウ   Joe Suzuki   鈴木　讓    所属   追手門学院大学  理工学部 数理・データサイエンス学科    職種   教授
発行・発表の年月	2024/08/21
形態種別	論文
査読	査読あり
標題	Learning under singularity: an information criterion improving WBIC and sBIC
執筆形態	共著・編著（代表編著を除く）
掲載誌名	Japanese Journal of Statistics and Data Science
出版社・発行元	Springer Science and Business Media LLC
著者・共著者	Lirui Liu,Joe Suzuki
概要	Abstract We introduce a novel information criterion, termed learning under singularity (LS), designed to enhance the functionality of the widely applicable Bayes information criterion (WBIC) and the singular Bayesian information criterion (sBIC). LS is effective without regularity constraints and demonstrates stability. Watanabe defined a statistical model or a learning machine as regular if the mapping from a parameter to a probability distribution is one-to-one and its Fisher information matrix is positive definite. In contrast, models not meeting these conditions are termed singular. Over the past decade, several information criteria for singular cases have been proposed, including WBIC and sBIC. WBIC is applicable in non-regular scenarios but faces challenges with large sample sizes and redundant estimation of known learning coefficients. Conversely, sBIC is limited in its broader application due to its dependence on maximum likelihood estimates. LS addresses these limitations by enhancing the utility of both WBIC and sBIC. It incorporates the empirical loss from the widely applicable information criterion (WAIC) to represent the goodness of fit to the statistical model, along with a penalty term similar to that of sBIC. This approach offers a flexible and robust method for model selection, free from regularity constraints.
DOI	10.1007/s42081-024-00262-1
ISSN	2520-8756/2520-8764
PermalinkURL	https://link.springer.com/content/pdf/10.1007/s42081-024-00262-1.pdf
researchmap用URL	https://link.springer.com/article/10.1007/s42081-024-00262-1/fulltext.html