Skip navigation

Exact calculation of normalized maximum likelihood code length using fourier analysis

Exact calculation of normalized maximum likelihood code length using fourier analysis

Suzuki, Atsushi and Kenji, Yamanishi (2018) Exact calculation of normalized maximum likelihood code length using fourier analysis. In: 2018 IEEE International Symposium on Information Theory (ISIT). IEEE, pp. 1211-1215. ISBN 978-1538641026 ISSN 2157-8117 (Online) (doi:https://doi.org/10.1109/ISIT.2018.8437862)

Full text not available from this repository. (Request a copy)

Abstract

The normalized maximum likelihood code length has been widely used in model selection, and its favorable properties, such as its consistency and the upper bound of its statistical risk, have been demonstrated. This paper proposes a novel methodology for calculating the normalized maximum likelihood code length on the basis of Fourier analysis. Our methodology provides an efficient non-asymptotic calculation formula for exponential family models and an asymptotic calculation formula for general parametric models with a weaker assumption compared to that in previous work. 2018 International Symposium on Information Theory.

Item Type: Conference Proceedings
Title of Proceedings: 2018 IEEE International Symposium on Information Theory (ISIT)
Uncontrolled Keywords: nonasymptotic calculation formula, normalized maximum likelihood code length, fourier analysis, exponential family models
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Faculty / Department / Research Group: Faculty of Liberal Arts & Sciences
Faculty of Liberal Arts & Sciences > School of Computing & Mathematical Sciences (CAM)
Last Modified: 26 Jan 2021 15:20
Selected for GREAT 2016: None
Selected for GREAT 2017: None
Selected for GREAT 2018: None
Selected for GREAT 2019: None
Selected for REF2021: None
URI: http://gala.gre.ac.uk/id/eprint/30535

Actions (login required)

View Item View Item