Optimal design of priors constrained by external predictors

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985556%3A_____%2F17%3A00473911" target="_blank" >RIV/67985556:_____/17:00473911 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1016/j.ijar.2017.02.001" target="_blank" >http://dx.doi.org/10.1016/j.ijar.2017.02.001</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.ijar.2017.02.001" target="_blank" >10.1016/j.ijar.2017.02.001</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Optimal design of priors constrained by external predictors

Popis výsledku v původním jazyce

This paper exploits knowledge made available by an external source in the form of a predictive distribution in order to elicit a parameter prior. It uses the terminology of Bayesian transfer learning, one of many domains dealing with reasoning as coherent knowledge processing. An empirical solution of the addressed problem was provided in [19], based on an interpretation of the external predictor as an empirical distribution constructed from fictitious data. In this paper, two main contributions are provided. First, the problem is solved using formal hierarchical Bayesian modeling [25], and the knowledge transfer is achieved optimally, i.e. in the minimum-KLD sense. Second, this hierarchical setting yields a distribution on the set of possible priors, with the choice [19] acting as the base distribution. This allows randomized choices of the prior to be generated, avoiding costly and/or intractable estimation of this prior. It also provides measures of uncertainty in the prior choice, allowing subsequent learning tasks to be assessed for robustness to this prior choice. The instantiation of the method in already published applications in knowledge elicitation, recursive learning and flat cooperation of adaptive controllers is recalled, and prospective application domains are also mentioned.

Název v anglickém jazyce

Optimal design of priors constrained by external predictors

Popis výsledku anglicky

This paper exploits knowledge made available by an external source in the form of a predictive distribution in order to elicit a parameter prior. It uses the terminology of Bayesian transfer learning, one of many domains dealing with reasoning as coherent knowledge processing. An empirical solution of the addressed problem was provided in [19], based on an interpretation of the external predictor as an empirical distribution constructed from fictitious data. In this paper, two main contributions are provided. First, the problem is solved using formal hierarchical Bayesian modeling [25], and the knowledge transfer is achieved optimally, i.e. in the minimum-KLD sense. Second, this hierarchical setting yields a distribution on the set of possible priors, with the choice [19] acting as the base distribution. This allows randomized choices of the prior to be generated, avoiding costly and/or intractable estimation of this prior. It also provides measures of uncertainty in the prior choice, allowing subsequent learning tasks to be assessed for robustness to this prior choice. The instantiation of the method in already published applications in knowledge elicitation, recursive learning and flat cooperation of adaptive controllers is recalled, and prospective application domains are also mentioned.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GA16-09848S" target="_blank" >GA16-09848S: Racionalita a uvažování</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

International Journal of Approximate Reasoning

ISSN

0888-613X

e-ISSN

—

Svazek periodika

84

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

9

Strana od-do

150-158

Kód UT WoS článku

000400231600008

EID výsledku v databázi Scopus

2-s2.0-85015609196