Running Markov Chain Monte Carlo on Modern Hardware and Software Article Swipe

PDF

Pavel Sountsov , Colin Carroll , Matthew D. Hoffman ·

YOU? · · 2024 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2411.04260

Today, cheap numerical hardware offers huge amounts of parallel computing power, much of which is used for the task of fitting neural networks to data. Adoption of this hardware to accelerate statistical Markov chain Monte Carlo (MCMC) applications has been much slower. In this chapter, we suggest some patterns for speeding up MCMC workloads using the hardware (e.g., GPUs, TPUs) and software (e.g., PyTorch, JAX) that have driven progress in deep learning over the last fifteen years or so. We offer some intuitions for why these new systems are so well suited to MCMC, and show some examples (with code) where we use them to achieve dramatic speedups over a CPU-based workflow. Finally, we discuss some potential pitfalls to watch out for.

Related Topics

Concepts

Markov chain Monte Carlo Computer science Monte Carlo method Software Markov chain Operating system Mathematics Statistics Machine learning

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2411.04260
PDF: https://arxiv.org/pdf/2411.04260
OA Status: green
Related Works: 10
OpenAlex ID: https://openalex.org/W4404404689

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4404404689

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2411.04260

Digital Object Identifier
Title: Running Markov Chain Monte Carlo on Modern Hardware and Software

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2024

Year of publication
Publication date: 2024-11-06

Full publication date if available
Authors: Pavel Sountsov, Colin Carroll, Matthew D. Hoffman

List of authors in order
Landing page: https://arxiv.org/abs/2411.04260

Publisher landing page
PDF URL: https://arxiv.org/pdf/2411.04260

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2411.04260

Direct OA link when available
Concepts: Markov chain Monte Carlo, Computer science, Monte Carlo method, Software, Markov chain, Operating system, Mathematics, Statistics, Machine learning

Top concepts (fields/topics) attached by OpenAlex
Cited by: 0

Total citation count in OpenAlex
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4404404689
doi	https://doi.org/10.48550/arxiv.2411.04260
ids.doi	https://doi.org/10.48550/arxiv.2411.04260
ids.openalex	https://openalex.org/W4404404689
fwci
type	preprint
title	Running Markov Chain Monte Carlo on Modern Hardware and Software
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T11195
topics[0].field.id	https://openalex.org/fields/18
topics[0].field.display_name	Decision Sciences
topics[0].score	0.2540000081062317
topics[0].domain.id	https://openalex.org/domains/2
topics[0].domain.display_name	Social Sciences
topics[0].subfield.id	https://openalex.org/subfields/1803
topics[0].subfield.display_name	Management Science and Operations Research
topics[0].display_name	Simulation Techniques and Applications
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C111350023
concepts[0].level	3
concepts[0].score	0.697135329246521
concepts[0].wikidata	https://www.wikidata.org/wiki/Q1191869
concepts[0].display_name	Markov chain Monte Carlo
concepts[1].id	https://openalex.org/C41008148
concepts[1].level	0
concepts[1].score	0.6482656598091125
concepts[1].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[1].display_name	Computer science
concepts[2].id	https://openalex.org/C19499675
concepts[2].level	2
concepts[2].score	0.5952122807502747
concepts[2].wikidata	https://www.wikidata.org/wiki/Q232207
concepts[2].display_name	Monte Carlo method
concepts[3].id	https://openalex.org/C2777904410
concepts[3].level	2
concepts[3].score	0.5575463175773621
concepts[3].wikidata	https://www.wikidata.org/wiki/Q7397
concepts[3].display_name	Software
concepts[4].id	https://openalex.org/C98763669
concepts[4].level	2
concepts[4].score	0.5360645651817322
concepts[4].wikidata	https://www.wikidata.org/wiki/Q176645
concepts[4].display_name	Markov chain
concepts[5].id	https://openalex.org/C111919701
concepts[5].level	1
concepts[5].score	0.1827675700187683
concepts[5].wikidata	https://www.wikidata.org/wiki/Q9135
concepts[5].display_name	Operating system
concepts[6].id	https://openalex.org/C33923547
concepts[6].level	0
concepts[6].score	0.1414242386817932
concepts[6].wikidata	https://www.wikidata.org/wiki/Q395
concepts[6].display_name	Mathematics
concepts[7].id	https://openalex.org/C105795698
concepts[7].level	1
concepts[7].score	0.07426449656486511
concepts[7].wikidata	https://www.wikidata.org/wiki/Q12483
concepts[7].display_name	Statistics
concepts[8].id	https://openalex.org/C119857082
concepts[8].level	1
concepts[8].score	0.0675700306892395
concepts[8].wikidata	https://www.wikidata.org/wiki/Q2539
concepts[8].display_name	Machine learning
keywords[0].id	https://openalex.org/keywords/markov-chain-monte-carlo
keywords[0].score	0.697135329246521
keywords[0].display_name	Markov chain Monte Carlo
keywords[1].id	https://openalex.org/keywords/computer-science
keywords[1].score	0.6482656598091125
keywords[1].display_name	Computer science
keywords[2].id	https://openalex.org/keywords/monte-carlo-method
keywords[2].score	0.5952122807502747
keywords[2].display_name	Monte Carlo method
keywords[3].id	https://openalex.org/keywords/software
keywords[3].score	0.5575463175773621
keywords[3].display_name	Software
keywords[4].id	https://openalex.org/keywords/markov-chain
keywords[4].score	0.5360645651817322
keywords[4].display_name	Markov chain
keywords[5].id	https://openalex.org/keywords/operating-system
keywords[5].score	0.1827675700187683
keywords[5].display_name	Operating system
keywords[6].id	https://openalex.org/keywords/mathematics
keywords[6].score	0.1414242386817932
keywords[6].display_name	Mathematics
keywords[7].id	https://openalex.org/keywords/statistics
keywords[7].score	0.07426449656486511
keywords[7].display_name	Statistics
keywords[8].id	https://openalex.org/keywords/machine-learning
keywords[8].score	0.0675700306892395
keywords[8].display_name	Machine learning
language	en
locations[0].id	pmh:oai:arXiv.org:2411.04260
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2411.04260
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2411.04260
locations[1].id	doi:10.48550/arxiv.2411.04260
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license	cc-by
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id	https://openalex.org/licenses/cc-by
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2411.04260
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5008991598
authorships[0].author.orcid
authorships[0].author.display_name	Pavel Sountsov
authorships[0].author_position	first
authorships[0].raw_author_name	Sountsov, Pavel
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5104946405
authorships[1].author.orcid
authorships[1].author.display_name	Colin Carroll
authorships[1].author_position	middle
authorships[1].raw_author_name	Carroll, Colin
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5109851187
authorships[2].author.orcid
authorships[2].author.display_name	Matthew D. Hoffman
authorships[2].author_position	last
authorships[2].raw_author_name	Hoffman, Matthew D.
authorships[2].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2411.04260
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Running Markov Chain Monte Carlo on Modern Hardware and Software
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T11195
primary_topic.field.id	https://openalex.org/fields/18
primary_topic.field.display_name	Decision Sciences
primary_topic.score	0.2540000081062317
primary_topic.domain.id	https://openalex.org/domains/2
primary_topic.domain.display_name	Social Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1803
primary_topic.subfield.display_name	Management Science and Operations Research
primary_topic.display_name	Simulation Techniques and Applications
related_works	https://openalex.org/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W2151689585, https://openalex.org/W2380816257, https://openalex.org/W3087071515, https://openalex.org/W4283726152, https://openalex.org/W2390279801, https://openalex.org/W1525770572, https://openalex.org/W4391913857
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2411.04260
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2411.04260
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2411.04260
primary_location.id	pmh:oai:arXiv.org:2411.04260
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2411.04260
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2411.04260
publication_date	2024-11-06
publication_year	2024
referenced_works_count	0
abstract_inverted_index.a	109
abstract_inverted_index.In	42
abstract_inverted_index.We	79
abstract_inverted_index.in	69
abstract_inverted_index.is	14
abstract_inverted_index.of	7, 12, 19, 26
abstract_inverted_index.or	77
abstract_inverted_index.so	89
abstract_inverted_index.to	23, 29, 92, 104, 118
abstract_inverted_index.up	51
abstract_inverted_index.we	45, 101, 113
abstract_inverted_index.and	60, 94
abstract_inverted_index.are	88
abstract_inverted_index.for	16, 49, 83
abstract_inverted_index.has	38
abstract_inverted_index.new	86
abstract_inverted_index.out	120
abstract_inverted_index.so.	78
abstract_inverted_index.the	17, 55, 73
abstract_inverted_index.use	102
abstract_inverted_index.why	84
abstract_inverted_index.JAX)	64
abstract_inverted_index.MCMC	52
abstract_inverted_index.been	39
abstract_inverted_index.deep	70
abstract_inverted_index.for.	121
abstract_inverted_index.have	66
abstract_inverted_index.huge	5
abstract_inverted_index.last	74
abstract_inverted_index.much	11, 40
abstract_inverted_index.over	72, 108
abstract_inverted_index.show	95
abstract_inverted_index.some	47, 81, 96, 115
abstract_inverted_index.task	18
abstract_inverted_index.that	65
abstract_inverted_index.them	103
abstract_inverted_index.this	27, 43
abstract_inverted_index.used	15
abstract_inverted_index.well	90
abstract_inverted_index.(with	98
abstract_inverted_index.Carlo	35
abstract_inverted_index.GPUs,	58
abstract_inverted_index.MCMC,	93
abstract_inverted_index.Monte	34
abstract_inverted_index.TPUs)	59
abstract_inverted_index.chain	33
abstract_inverted_index.cheap	1
abstract_inverted_index.code)	99
abstract_inverted_index.data.	24
abstract_inverted_index.offer	80
abstract_inverted_index.these	85
abstract_inverted_index.using	54
abstract_inverted_index.watch	119
abstract_inverted_index.where	100
abstract_inverted_index.which	13
abstract_inverted_index.years	76
abstract_inverted_index.(MCMC)	36
abstract_inverted_index.(e.g.,	57, 62
abstract_inverted_index.Markov	32
abstract_inverted_index.Today,	0
abstract_inverted_index.driven	67
abstract_inverted_index.neural	21
abstract_inverted_index.offers	4
abstract_inverted_index.power,	10
abstract_inverted_index.suited	91
abstract_inverted_index.achieve	105
abstract_inverted_index.amounts	6
abstract_inverted_index.discuss	114
abstract_inverted_index.fifteen	75
abstract_inverted_index.fitting	20
abstract_inverted_index.slower.	41
abstract_inverted_index.suggest	46
abstract_inverted_index.systems	87
abstract_inverted_index.Adoption	25
abstract_inverted_index.Finally,	112
abstract_inverted_index.PyTorch,	63
abstract_inverted_index.chapter,	44
abstract_inverted_index.dramatic	106
abstract_inverted_index.examples	97
abstract_inverted_index.hardware	3, 28, 56
abstract_inverted_index.learning	71
abstract_inverted_index.networks	22
abstract_inverted_index.parallel	8
abstract_inverted_index.patterns	48
abstract_inverted_index.pitfalls	117
abstract_inverted_index.progress	68
abstract_inverted_index.software	61
abstract_inverted_index.speeding	50
abstract_inverted_index.speedups	107
abstract_inverted_index.CPU-based	110
abstract_inverted_index.computing	9
abstract_inverted_index.numerical	2
abstract_inverted_index.potential	116
abstract_inverted_index.workflow.	111
abstract_inverted_index.workloads	53
abstract_inverted_index.accelerate	30
abstract_inverted_index.intuitions	82
abstract_inverted_index.statistical	31
abstract_inverted_index.applications	37
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	3
citation_normalized_percentile