Ideal-Theoretic Strategies for Asymptotic Approximation of Marginal Likelihood Integrals
AbstractThe accurate asymptotic evaluation of marginal likelihood integrals is a fundamental problem in Bayesian statistics. Following the approach introduced by Watanabe, we translate this into a problem of computational algebraic geometry, namely, to determine the real log canonical threshold of a polynomial ideal, and we present effective methods for solving this problem. Our results are based on resolution of singularities. They apply to parametric models where the Kullback-Leibler distance is upper and lower bounded by scalar multiples of some sum of squared real analytic functions. Such models include finite state discrete models.
How to Cite
LIN, Shaowei. Ideal-Theoretic Strategies for Asymptotic Approximation of Marginal Likelihood Integrals. Journal of Algebraic Statistics, [S.l.], v. 8, n. 1, feb. 2017. ISSN 1309-3452. Available at: <http://www.jalgstat.com/jalgstat/article/view/47>. Date accessed: 21 sep. 2017. doi: https://doi.org/10.18409/jas.v8i1.47.
Articles - regular submission
computational algebra; asymptotic approximation; marginal likelihood; learning coefficient; real log canonical threshold
Upon submission, authors agree with the following Article Submission Agreement. Once the papers are published, authors are required to use the DOI link provided on all websites and arXiv postings of their paper.