Necessary and sufficient conditions of proper estimators based on self density ratio for unnormalized statistical models

DOI10.1016/J.NEUNET.2017.11.018MaRDI QIDQ2179310zbMATH OpenOpenAlexWikidataFDO

Authors Kazuyuki Hiraoka, Toshihiko Hamada, Gen Hori

Publication date 12 May 2020

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.neunet.2017.11.018

zbMATH Keywords

consistencynon-local scoring rulesscore matchingself density ratiounnormalized statistical model

Mathematics Subject Classification ID

Estimation in multivariate analysis (62H12) Neural nets and related approaches to inference from stochastic processes (62M45) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• On necessary and sufficient conditions for the self-normalized central limit theorem
• Density estimation for samples satisfying a certain absolute regularity condition
• Necessary and sufficient condition for the existence of a limit distribution of the nearest-neighbour densitiy estimator
• Self-consistent density estimation in the presence of errors-in-variables
• Bayes estimates of the density of sufficient statistics for the normal distribution and their statistical properties
• scientific article; zbMATH DE number 879737
• scientific article; zbMATH DE number 3938304
• Necessary and sufficient conditions for the consistency of maximum likelihood estimators
• Asymptotic normality of unbiased estimators in the case of an absolutely continuous multiparameter exponential family

Cites work

• 10.1162/153244303322533223
• A Fast Learning Algorithm for Deep Belief Nets
• A Two-Layer Model of Natural Stimuli Estimated with Score Matching
• Bounds on the maximum number of factors in designs with two distinct groups of factors
• Covariate shift adaptation by importance weighted cross validation
• Density ratio estimation in machine learning. Foreword by Thomas G. Dietterich
• Dimensionality reduction for density ratio estimation in high-dimensional spaces
• Estimating Squared-Loss Mutual Information for Independent Component Analysis
• Estimation of non-normalized statistical models by score matching
• Functional Bregman Divergence and Bayesian Estimation of Distributions
• Game theory, maximum entropy, minimum discrepancy and robust Bayesian decision theory
• scientific article; zbMATH DE number 5296741 (Why is no real title available?)
• scientific article; zbMATH DE number 51940 (Why is no real title available?)
• scientific article; zbMATH DE number 1220667 (Why is no real title available?)
• scientific article; zbMATH DE number 509169 (Why is no real title available?)
• scientific article; zbMATH DE number 854710 (Why is no real title available?)
• scientific article; zbMATH DE number 6276120 (Why is no real title available?)
• Improving predictive inference under covariate shift by weighting the log-likelihood function
• Inference based on estimating functions in the presence of nuisance parameters. With comments and rejoinder
• Introduction to Smooth Manifolds
• Local proper scoring rules of order two
• Markov Random Field Modeling in Image Analysis
• Proper local scoring rules
• Representational Power of Restricted Boltzmann Machines and Deep Belief Networks
• Some extensions of score matching
• Sufficient dimension reduction via squared-loss mutual information estimation
• Training Products of Experts by Minimizing Contrastive Divergence

Cited in

(1)

• A numerically stable algorithm for integrating Bayesian models using Markov melding

Describes a project that uses

Uses Software

• darch

This page was built for publication: Necessary and sufficient conditions of proper estimators based on self density ratio for unnormalized statistical models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2179310)