Presentation 2014-11-17
Entropy Estimators Based on Simple Linear Regression
Hideitsu HINO, Kensuke KOSHIJIMA, Noboru MURATA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Three differential entropy estimators are proposed based on the second order expansion of the probability mass around the inspection point with respect to the distance from the point. In the second order expantion of the probability mass function, the constant term corresponds to the value of the probability density function at the inspection point. Simple linear regression is utilized to estimate the values of density function. The density estimates at every given data points are averaged to obtain entropy estimators. Another entropy estimator, which directly estimates entropy by linear regression, is also proposed. The proposed three estimators are shown to perform well through numerical experiments for various probability distributions.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Entropy / Simple Regression / Density Estimation / Sampling
Paper # IBISML2014-39
Date of Issue

Conference Information
Committee IBISML
Conference Date 2014/11/10(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Information-Based Induction Sciences and Machine Learning (IBISML)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Entropy Estimators Based on Simple Linear Regression
Sub Title (in English)
Keyword(1) Entropy
Keyword(2) Simple Regression
Keyword(3) Density Estimation
Keyword(4) Sampling
1st Author's Name Hideitsu HINO
1st Author's Affiliation University of Tsukuba()
2nd Author's Name Kensuke KOSHIJIMA
2nd Author's Affiliation Recruit Jobs Co., Ltd.
3rd Author's Name Noboru MURATA
3rd Author's Affiliation Waseda University
Date 2014-11-17
Paper # IBISML2014-39
Volume (vol) vol.114
Number (no) 306
Page pp.pp.-
#Pages 8
Date of Issue