Conference item icon

Conference item

Output-sensitive Adaptive Metropolis-Hastings for probabilistic programs

Abstract:

We introduce an adaptive output-sensitive Metropolis-Hastings algorithm for probabilistic models expressed as programs, Adaptive Lightweight Metropolis-Hastings (AdLMH). This algorithm extends Lightweight Metropolis-Hastings (LMH) by adjusting the probabilities of proposing random variables for modification to improve convergence of the program output. We show that AdLMH converges to the correct equilibrium distribution and compare convergence of AdLMH to that of LMH on several test problems ...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.1007/978-3-319-23525-7_19
Publisher:
Springer
Host title:
Lecture Notes in Computer Science: ECML PKDD 2015: Machine Learning and Knowledge Discovery in Databases
Journal:
Lecture Notes in Computer Science: ECML PKDD 2015: Machine Learning and Knowledge Discovery in Databases More from this journal
Volume:
9285
Pages:
311-326
Publication date:
2015-08-29
DOI:
ISSN:
1611-3349 and 0302-9743
ISBN:
9783319235240
Keywords:
Pubs id:
pubs:579427
UUID:
uuid:0ac75ab0-4217-4da3-9049-54eae28df111
Local pid:
pubs:579427
Source identifiers:
579427
Deposit date:
2017-03-23

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP