File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ISIT.2018.8437862
- Scopus: eid_2-s2.0-85052474975
- Find via
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Exact Calculation of Normalized Maximum Likelihood Code Length Using Fourier Analysis
| Title | Exact Calculation of Normalized Maximum Likelihood Code Length Using Fourier Analysis |
|---|---|
| Authors | |
| Issue Date | 2018 |
| Citation | IEEE International Symposium on Information Theory - Proceedings, 2018, v. 2018-June, p. 1211-1215 How to Cite? |
| 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. A full version of this paper is accessible at https://arxiv.org/abs/1801.03705 [21] |
| Persistent Identifier | http://hdl.handle.net/10722/354122 |
| ISSN | 2023 SCImago Journal Rankings: 0.696 |
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.author | Suzuki, Atsushi | - |
| dc.contributor.author | Yamanishi, Kenji | - |
| dc.date.accessioned | 2025-02-07T08:46:36Z | - |
| dc.date.available | 2025-02-07T08:46:36Z | - |
| dc.date.issued | 2018 | - |
| dc.identifier.citation | IEEE International Symposium on Information Theory - Proceedings, 2018, v. 2018-June, p. 1211-1215 | - |
| dc.identifier.issn | 2157-8095 | - |
| dc.identifier.uri | http://hdl.handle.net/10722/354122 | - |
| dc.description.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. A full version of this paper is accessible at https://arxiv.org/abs/1801.03705 [21] | - |
| dc.language | eng | - |
| dc.relation.ispartof | IEEE International Symposium on Information Theory - Proceedings | - |
| dc.title | Exact Calculation of Normalized Maximum Likelihood Code Length Using Fourier Analysis | - |
| dc.type | Conference_Paper | - |
| dc.description.nature | link_to_subscribed_fulltext | - |
| dc.identifier.doi | 10.1109/ISIT.2018.8437862 | - |
| dc.identifier.scopus | eid_2-s2.0-85052474975 | - |
| dc.identifier.volume | 2018-June | - |
| dc.identifier.spage | 1211 | - |
| dc.identifier.epage | 1215 | - |