The finite model theory of Bayesian networks: Descriptive complexity

Fabio Gagliardi Cozman; Denis Deratani Mauá

doi:10.24963/ijcai.2018/727

The finite model theory of Bayesian networks: Descriptive complexity

Fabio Gagliardi Cozman, Denis Deratani Mauá

Research output: Contribution to conference › Conference Paper

Abstract

© 2018 International Joint Conferences on Artificial Intelligence.All right reserved. We adapt the theory of descriptive complexity to encompass Bayesian networks, so as to quantify the expressivity of Bayesian network specifications based on predicates and quantifiers. We show that Bayesian network specifications that employ first-order quantification capture the complexity class PP; by allowing quantification over predicates, the resulting Bayesian network specifications capture each class in the hierarchy PPNP...NP , a result that does not seem to have equivalent in the literature.

Original language	American English
Pages	5229-5233
Number of pages	5
DOIs	https://doi.org/10.24963/ijcai.2018/727
State	Published - 1 Jan 2018
Externally published	Yes
Event	IJCAI International Joint Conference on Artificial Intelligence - Duration: 1 Jan 2018 → …

Conference

Conference	IJCAI International Joint Conference on Artificial Intelligence
Period	1/01/18 → …

Access to Document

10.24963/ijcai.2018/727

Cite this

@conference{9a43699dd2b3469886e7166ebaf484aa,

title = "The finite model theory of Bayesian networks: Descriptive complexity",

abstract = "{\textcopyright} 2018 International Joint Conferences on Artificial Intelligence.All right reserved. We adapt the theory of descriptive complexity to encompass Bayesian networks, so as to quantify the expressivity of Bayesian network specifications based on predicates and quantifiers. We show that Bayesian network specifications that employ first-order quantification capture the complexity class PP; by allowing quantification over predicates, the resulting Bayesian network specifications capture each class in the hierarchy PPNP...NP , a result that does not seem to have equivalent in the literature.",

author = "Cozman, {Fabio Gagliardi} and Mau{\'a}, {Denis Deratani}",

year = "2018",

month = jan,

day = "1",

doi = "10.24963/ijcai.2018/727",

language = "American English",

pages = "5229--5233",

note = "IJCAI International Joint Conference on Artificial Intelligence ; Conference date: 01-01-2018",

}

TY - CONF

T1 - The finite model theory of Bayesian networks: Descriptive complexity

AU - Cozman, Fabio Gagliardi

AU - Mauá, Denis Deratani

PY - 2018/1/1

Y1 - 2018/1/1

N2 - © 2018 International Joint Conferences on Artificial Intelligence.All right reserved. We adapt the theory of descriptive complexity to encompass Bayesian networks, so as to quantify the expressivity of Bayesian network specifications based on predicates and quantifiers. We show that Bayesian network specifications that employ first-order quantification capture the complexity class PP; by allowing quantification over predicates, the resulting Bayesian network specifications capture each class in the hierarchy PPNP...NP , a result that does not seem to have equivalent in the literature.

AB - © 2018 International Joint Conferences on Artificial Intelligence.All right reserved. We adapt the theory of descriptive complexity to encompass Bayesian networks, so as to quantify the expressivity of Bayesian network specifications based on predicates and quantifiers. We show that Bayesian network specifications that employ first-order quantification capture the complexity class PP; by allowing quantification over predicates, the resulting Bayesian network specifications capture each class in the hierarchy PPNP...NP , a result that does not seem to have equivalent in the literature.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85055693437&origin=inward

UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85055693437&origin=inward

U2 - 10.24963/ijcai.2018/727

DO - 10.24963/ijcai.2018/727

M3 - Conference Paper

SP - 5229

EP - 5233

T2 - IJCAI International Joint Conference on Artificial Intelligence

Y2 - 1 January 2018

ER -

The finite model theory of Bayesian networks: Descriptive complexity

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this