國立虎尾科技大學 |

Towards Compositional Probabilistic Programming.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Towards Compositional Probabilistic Programming./
Author:	Sennesh, Eli.
Description:	1 online resource (195 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 85-03, Section: B.
Contained By:	Dissertations Abstracts International85-03B.
Subject:	Computer science. -
Online resource:	click for full text (PQDT)
ISBN:	9798380316699

Towards Compositional Probabilistic Programming.
Sennesh, Eli.

Towards Compositional Probabilistic Programming. - 1 online resource (195 pages)

Source: Dissertations Abstracts International, Volume: 85-03, Section: B.

Thesis (Ph.D.)--Northeastern University, 2023.

Includes bibliographical references

Converging evidence from the behavioral sciences suggests that inference in probabilistic generative models can capture how human and animal subjects solve a variety of cognitive tasks involving uncertainty. In fact, such evidence has accumulated more quickly than bespoke computational modeling can keep pace, contributing impetus to the development of probabilistic programming systems to reduce the duplication of effort. Among these, deep probabilistic programming systems enable the integration of deep neural networks into probabilistic generative models as powerful function approximators. In this dissertation, I provide compositional tools for reasoning about model structure and inference in the deep probabilistic programming system Probabilistic Torch. I begin with a case report about applying deep probabilistic programming to neuroimaging, including mean-field inference and a nontrivial stochastic gradient estimator for the training objective. I then dive into my work on training neural proposals to break down a complex joint distribution into a series of simpler complete conditional distributions. I then describe my contributions to a domain-specific language of inference combinators for composing importance sampling strategies in deep probabilistic programs, including an inference combinators implementation of the previous decompositional sampling strategy. I finally overview my work on providing categorical foundations in which to ground the semantics of deep probabilistic programs and reason compositionally about their model structure and inference strategies. I then close the dissertation by discussing how compositionality can help probabilistic machine learning scale up towards brain-sized inference problems.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798380316699Subjects--Topical Terms:

573171
Computer science.
Subjects--Index Terms:

Probabilistic programmingIndex Terms--Genre/Form:

554714
Electronic books.

Towards Compositional Probabilistic Programming.
LDR:03150ntm a22003857 4500 001 1148721
005 20240930100127.5
006 m o d
007 cr bn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798380316699
035 $a (MiAaPQ)AAI30639137
035 $a AAI30639137
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Sennesh, Eli. $3 1474761
245 1 0 $a Towards Compositional Probabilistic Programming.
264 0 $c 2023
300 $a 1 online resource (195 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 85-03, Section: B.
500 $a Advisor: van de Meent, Jan-Willem;Holtzen, Steven;Wand, Mitchell;Barrett, Lisa Feldman;Quigley, Karen.
502 $a Thesis (Ph.D.)--Northeastern University, 2023.
504 $a Includes bibliographical references
520 $a Converging evidence from the behavioral sciences suggests that inference in probabilistic generative models can capture how human and animal subjects solve a variety of cognitive tasks involving uncertainty. In fact, such evidence has accumulated more quickly than bespoke computational modeling can keep pace, contributing impetus to the development of probabilistic programming systems to reduce the duplication of effort. Among these, deep probabilistic programming systems enable the integration of deep neural networks into probabilistic generative models as powerful function approximators. In this dissertation, I provide compositional tools for reasoning about model structure and inference in the deep probabilistic programming system Probabilistic Torch. I begin with a case report about applying deep probabilistic programming to neuroimaging, including mean-field inference and a nontrivial stochastic gradient estimator for the training objective. I then dive into my work on training neural proposals to break down a complex joint distribution into a series of simpler complete conditional distributions. I then describe my contributions to a domain-specific language of inference combinators for composing importance sampling strategies in deep probabilistic programs, including an inference combinators implementation of the previous decompositional sampling strategy. I finally overview my work on providing categorical foundations in which to ground the semantics of deep probabilistic programs and reason compositionally about their model structure and inference strategies. I then close the dissertation by discussing how compositionality can help probabilistic machine learning scale up towards brain-sized inference problems.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
650 4 $a Statistics. $3 556824
653 $a Probabilistic programming
653 $a Computational modeling
653 $a Machine learning
653 $a Neuroimaging
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0463
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Northeastern University. $b Computer Science. $3 1464678
773 0 $t Dissertations Abstracts International $g 85-03B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30639137 $z click for full text (PQDT)