On some singularities in parameter estimation problems

Shun Ichi Amari; Marat V. Burnashev

doi:10.1109/isit.2003.1228243

On some singularities in parameter estimation problems

Shun Ichi Amari
, Marat V. Burnashev

RIKEN
Russian Academy of Sciences

Research output: Contribution to journal › Conference article › peer-review

1 Scopus citations

Abstract

Assume that there are two identical remote objects and we want to estimate the distance to the closest of them and the distance between the objects. For that purpose a "radar" - like device is used, and the signal observed is the sum of signals reflected by each object, corrupted by white Gaussian noise. Singularity (i.e. very poor performance of any estimate) in this problem will occur if objects are very close to each other. We demonstrate this inherited singularity on the example of the ML-estimate.

Original language	English
Pages (from-to)	229
Number of pages	1
Journal	IEEE International Symposium on Information Theory - Proceedings
DOIs	https://doi.org/10.1109/isit.2003.1228243
State	Published - 2003
Externally published	Yes
Event	Proceedings 2003 IEEE International Symposium on Information Theory (ISIT) - Yokohama, Japan Duration: 29 Jun 2003 → 4 Jul 2003

Access to Document

10.1109/isit.2003.1228243

Cite this

@article{cb77f4ed87b4476189cc0ff51bef891b,

title = "On some singularities in parameter estimation problems",

abstract = "Assume that there are two identical remote objects and we want to estimate the distance to the closest of them and the distance between the objects. For that purpose a {"}radar{"} - like device is used, and the signal observed is the sum of signals reflected by each object, corrupted by white Gaussian noise. Singularity (i.e. very poor performance of any estimate) in this problem will occur if objects are very close to each other. We demonstrate this inherited singularity on the example of the ML-estimate.",

author = "Amari, \{Shun Ichi\} and Burnashev, \{Marat V.\}",

year = "2003",

doi = "10.1109/isit.2003.1228243",

language = "英語",

pages = "229",

journal = "IEEE International Symposium on Information Theory - Proceedings",

issn = "2157-8096",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "Proceedings 2003 IEEE International Symposium on Information Theory (ISIT) ; Conference date: 29-06-2003 Through 04-07-2003",

}

TY - JOUR

T1 - On some singularities in parameter estimation problems

AU - Amari, Shun Ichi

AU - Burnashev, Marat V.

PY - 2003

Y1 - 2003

N2 - Assume that there are two identical remote objects and we want to estimate the distance to the closest of them and the distance between the objects. For that purpose a "radar" - like device is used, and the signal observed is the sum of signals reflected by each object, corrupted by white Gaussian noise. Singularity (i.e. very poor performance of any estimate) in this problem will occur if objects are very close to each other. We demonstrate this inherited singularity on the example of the ML-estimate.

AB - Assume that there are two identical remote objects and we want to estimate the distance to the closest of them and the distance between the objects. For that purpose a "radar" - like device is used, and the signal observed is the sum of signals reflected by each object, corrupted by white Gaussian noise. Singularity (i.e. very poor performance of any estimate) in this problem will occur if objects are very close to each other. We demonstrate this inherited singularity on the example of the ML-estimate.

UR - https://www.scopus.com/pages/publications/0141973665

U2 - 10.1109/isit.2003.1228243

DO - 10.1109/isit.2003.1228243

M3 - 会議記事

AN - SCOPUS:0141973665

SN - 2157-8096

SP - 229

JO - IEEE International Symposium on Information Theory - Proceedings

JF - IEEE International Symposium on Information Theory - Proceedings

T2 - Proceedings 2003 IEEE International Symposium on Information Theory (ISIT)

Y2 - 29 June 2003 through 4 July 2003

ER -

On some singularities in parameter estimation problems

Abstract

Access to Document

Other files and links

Fingerprint

Cite this