The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Les limites inférieures de la théorie de l'information du risque bayésien ont été étudiées pour un problème d'estimation de paramètres dans un contexte bayésien. Des études antérieures ont prouvé la limite inférieure du risque bayésien d'une manière différente et ont caractérisé la limite inférieure via différentes quantités telles que l'information mutuelle, l'équation de Sibson. α-l'information mutuelle, f-divergence, et celle de Csiszár f-informativité. Dans cet article, nous introduisons une inégalité appelée « méta-borne pour les limites inférieures du risque bayésien » et montrons que les résultats précédents peuvent être dérivés de cette inégalité.
Shota SAITO
Gunma University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Shota SAITO, "Meta-Bound on Lower Bounds of Bayes Risk in Parameter Estimation" in IEICE TRANSACTIONS on Fundamentals,
vol. E107-A, no. 3, pp. 503-509, March 2024, doi: 10.1587/transfun.2023TAP0002.
Abstract: Information-theoretic lower bounds of the Bayes risk have been investigated for a problem of parameter estimation in a Bayesian setting. Previous studies have proven the lower bound of the Bayes risk in a different manner and characterized the lower bound via different quantities such as mutual information, Sibson's α-mutual information, f-divergence, and Csiszár's f-informativity. In this paper, we introduce an inequality called a “meta-bound for lower bounds of the Bayes risk” and show that the previous results can be derived from this inequality.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2023TAP0002/_p
Copier
@ARTICLE{e107-a_3_503,
author={Shota SAITO, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Meta-Bound on Lower Bounds of Bayes Risk in Parameter Estimation},
year={2024},
volume={E107-A},
number={3},
pages={503-509},
abstract={Information-theoretic lower bounds of the Bayes risk have been investigated for a problem of parameter estimation in a Bayesian setting. Previous studies have proven the lower bound of the Bayes risk in a different manner and characterized the lower bound via different quantities such as mutual information, Sibson's α-mutual information, f-divergence, and Csiszár's f-informativity. In this paper, we introduce an inequality called a “meta-bound for lower bounds of the Bayes risk” and show that the previous results can be derived from this inequality.},
keywords={},
doi={10.1587/transfun.2023TAP0002},
ISSN={1745-1337},
month={March},}
Copier
TY - JOUR
TI - Meta-Bound on Lower Bounds of Bayes Risk in Parameter Estimation
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 503
EP - 509
AU - Shota SAITO
PY - 2024
DO - 10.1587/transfun.2023TAP0002
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E107-A
IS - 3
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - March 2024
AB - Information-theoretic lower bounds of the Bayes risk have been investigated for a problem of parameter estimation in a Bayesian setting. Previous studies have proven the lower bound of the Bayes risk in a different manner and characterized the lower bound via different quantities such as mutual information, Sibson's α-mutual information, f-divergence, and Csiszár's f-informativity. In this paper, we introduce an inequality called a “meta-bound for lower bounds of the Bayes risk” and show that the previous results can be derived from this inequality.
ER -