Gradient Estimation via Differentiable Metropolis-Hastings Article Swipe
Gaurav Arya
,
Moritz Schauer
,
Ruben Seyer
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2406.14451
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2406.14451
Metropolis-Hastings estimates intractable expectations - can differentiating the algorithm estimate their gradients? The challenge is that Metropolis-Hastings trajectories are not conventionally differentiable due to the discrete accept/reject steps. Using a technique based on recoupling chains, our method differentiates through the Metropolis-Hastings sampler itself, allowing us to estimate gradients with respect to a parameter of otherwise intractable expectations. Our main contribution is a proof of strong consistency and a central limit theorem for our estimator under assumptions that hold in common Bayesian inference problems. The proofs augment the sampler chain with latent information, and formulate the estimator as a stopping tail functional of this augmented chain. We demonstrate our method on examples of Bayesian sensitivity analysis and optimizing a random walk Metropolis proposal.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2406.14451
- https://arxiv.org/pdf/2406.14451
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4399911872
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4399911872Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2406.14451Digital Object Identifier
- Title
-
Gradient Estimation via Differentiable Metropolis-HastingsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-06-20Full publication date if available
- Authors
-
Gaurav Arya, Moritz Schauer, Ruben SeyerList of authors in order
- Landing page
-
https://arxiv.org/abs/2406.14451Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2406.14451Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2406.14451Direct OA link when available
- Concepts
-
Metropolis–Hastings algorithm, Estimation, Differentiable function, Computer science, Mathematics, Artificial intelligence, Markov chain Monte Carlo, Economics, Mathematical analysis, Bayesian probability, ManagementTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4399911872 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2406.14451 |
| ids.doi | https://doi.org/10.48550/arxiv.2406.14451 |
| ids.openalex | https://openalex.org/W4399911872 |
| fwci | |
| type | preprint |
| title | Gradient Estimation via Differentiable Metropolis-Hastings |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T12056 |
| topics[0].field.id | https://openalex.org/fields/26 |
| topics[0].field.display_name | Mathematics |
| topics[0].score | 0.9764000177383423 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2613 |
| topics[0].subfield.display_name | Statistics and Probability |
| topics[0].display_name | Markov Chains and Monte Carlo Methods |
| topics[1].id | https://openalex.org/T10522 |
| topics[1].field.id | https://openalex.org/fields/27 |
| topics[1].field.display_name | Medicine |
| topics[1].score | 0.9366000294685364 |
| topics[1].domain.id | https://openalex.org/domains/4 |
| topics[1].domain.display_name | Health Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2741 |
| topics[1].subfield.display_name | Radiology, Nuclear Medicine and Imaging |
| topics[1].display_name | Medical Imaging Techniques and Applications |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C204693719 |
| concepts[0].level | 4 |
| concepts[0].score | 0.7288470268249512 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q910810 |
| concepts[0].display_name | Metropolis–Hastings algorithm |
| concepts[1].id | https://openalex.org/C96250715 |
| concepts[1].level | 2 |
| concepts[1].score | 0.626667857170105 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q965330 |
| concepts[1].display_name | Estimation |
| concepts[2].id | https://openalex.org/C202615002 |
| concepts[2].level | 2 |
| concepts[2].score | 0.605872392654419 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q783507 |
| concepts[2].display_name | Differentiable function |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.39255833625793457 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C33923547 |
| concepts[4].level | 0 |
| concepts[4].score | 0.34438616037368774 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[4].display_name | Mathematics |
| concepts[5].id | https://openalex.org/C154945302 |
| concepts[5].level | 1 |
| concepts[5].score | 0.24173858761787415 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[5].display_name | Artificial intelligence |
| concepts[6].id | https://openalex.org/C111350023 |
| concepts[6].level | 3 |
| concepts[6].score | 0.1697547733783722 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q1191869 |
| concepts[6].display_name | Markov chain Monte Carlo |
| concepts[7].id | https://openalex.org/C162324750 |
| concepts[7].level | 0 |
| concepts[7].score | 0.133323073387146 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q8134 |
| concepts[7].display_name | Economics |
| concepts[8].id | https://openalex.org/C134306372 |
| concepts[8].level | 1 |
| concepts[8].score | 0.0912410318851471 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q7754 |
| concepts[8].display_name | Mathematical analysis |
| concepts[9].id | https://openalex.org/C107673813 |
| concepts[9].level | 2 |
| concepts[9].score | 0.08998873829841614 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q812534 |
| concepts[9].display_name | Bayesian probability |
| concepts[10].id | https://openalex.org/C187736073 |
| concepts[10].level | 1 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q2920921 |
| concepts[10].display_name | Management |
| keywords[0].id | https://openalex.org/keywords/metropolis–hastings-algorithm |
| keywords[0].score | 0.7288470268249512 |
| keywords[0].display_name | Metropolis–Hastings algorithm |
| keywords[1].id | https://openalex.org/keywords/estimation |
| keywords[1].score | 0.626667857170105 |
| keywords[1].display_name | Estimation |
| keywords[2].id | https://openalex.org/keywords/differentiable-function |
| keywords[2].score | 0.605872392654419 |
| keywords[2].display_name | Differentiable function |
| keywords[3].id | https://openalex.org/keywords/computer-science |
| keywords[3].score | 0.39255833625793457 |
| keywords[3].display_name | Computer science |
| keywords[4].id | https://openalex.org/keywords/mathematics |
| keywords[4].score | 0.34438616037368774 |
| keywords[4].display_name | Mathematics |
| keywords[5].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[5].score | 0.24173858761787415 |
| keywords[5].display_name | Artificial intelligence |
| keywords[6].id | https://openalex.org/keywords/markov-chain-monte-carlo |
| keywords[6].score | 0.1697547733783722 |
| keywords[6].display_name | Markov chain Monte Carlo |
| keywords[7].id | https://openalex.org/keywords/economics |
| keywords[7].score | 0.133323073387146 |
| keywords[7].display_name | Economics |
| keywords[8].id | https://openalex.org/keywords/mathematical-analysis |
| keywords[8].score | 0.0912410318851471 |
| keywords[8].display_name | Mathematical analysis |
| keywords[9].id | https://openalex.org/keywords/bayesian-probability |
| keywords[9].score | 0.08998873829841614 |
| keywords[9].display_name | Bayesian probability |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2406.14451 |
| 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/2406.14451 |
| 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/2406.14451 |
| locations[1].id | doi:10.48550/arxiv.2406.14451 |
| 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 | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| 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.2406.14451 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5084515376 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-5615-0521 |
| authorships[0].author.display_name | Gaurav Arya |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Arya, Gaurav |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5059537394 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-3310-7915 |
| authorships[1].author.display_name | Moritz Schauer |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Schauer, Moritz |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5092172048 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Ruben Seyer |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Seyer, Ruben |
| 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/2406.14451 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Gradient Estimation via Differentiable Metropolis-Hastings |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T12056 |
| primary_topic.field.id | https://openalex.org/fields/26 |
| primary_topic.field.display_name | Mathematics |
| primary_topic.score | 0.9764000177383423 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2613 |
| primary_topic.subfield.display_name | Statistics and Probability |
| primary_topic.display_name | Markov Chains and Monte Carlo Methods |
| related_works | https://openalex.org/W2748952813, https://openalex.org/W4391375266, https://openalex.org/W4285277090, https://openalex.org/W4327738859, https://openalex.org/W1979597421, https://openalex.org/W2007980826, https://openalex.org/W2061531152, https://openalex.org/W3002753104, https://openalex.org/W2077600819, https://openalex.org/W2348722996 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2406.14451 |
| 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/2406.14451 |
| 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/2406.14451 |
| primary_location.id | pmh:oai:arXiv.org:2406.14451 |
| 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/2406.14451 |
| 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/2406.14451 |
| publication_date | 2024-06-20 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.- | 4 |
| abstract_inverted_index.a | 29, 51, 61, 67, 97, 117 |
| abstract_inverted_index.We | 105 |
| abstract_inverted_index.as | 96 |
| abstract_inverted_index.in | 78 |
| abstract_inverted_index.is | 14, 60 |
| abstract_inverted_index.of | 53, 63, 101, 111 |
| abstract_inverted_index.on | 32, 109 |
| abstract_inverted_index.to | 23, 45, 50 |
| abstract_inverted_index.us | 44 |
| abstract_inverted_index.Our | 57 |
| abstract_inverted_index.The | 12, 83 |
| abstract_inverted_index.and | 66, 92, 115 |
| abstract_inverted_index.are | 18 |
| abstract_inverted_index.can | 5 |
| abstract_inverted_index.due | 22 |
| abstract_inverted_index.for | 71 |
| abstract_inverted_index.not | 19 |
| abstract_inverted_index.our | 35, 72, 107 |
| abstract_inverted_index.the | 7, 24, 39, 86, 94 |
| abstract_inverted_index.hold | 77 |
| abstract_inverted_index.main | 58 |
| abstract_inverted_index.tail | 99 |
| abstract_inverted_index.that | 15, 76 |
| abstract_inverted_index.this | 102 |
| abstract_inverted_index.walk | 119 |
| abstract_inverted_index.with | 48, 89 |
| abstract_inverted_index.Using | 28 |
| abstract_inverted_index.based | 31 |
| abstract_inverted_index.chain | 88 |
| abstract_inverted_index.limit | 69 |
| abstract_inverted_index.proof | 62 |
| abstract_inverted_index.their | 10 |
| abstract_inverted_index.under | 74 |
| abstract_inverted_index.chain. | 104 |
| abstract_inverted_index.common | 79 |
| abstract_inverted_index.latent | 90 |
| abstract_inverted_index.method | 36, 108 |
| abstract_inverted_index.proofs | 84 |
| abstract_inverted_index.random | 118 |
| abstract_inverted_index.steps. | 27 |
| abstract_inverted_index.strong | 64 |
| abstract_inverted_index.augment | 85 |
| abstract_inverted_index.central | 68 |
| abstract_inverted_index.chains, | 34 |
| abstract_inverted_index.itself, | 42 |
| abstract_inverted_index.respect | 49 |
| abstract_inverted_index.sampler | 41, 87 |
| abstract_inverted_index.theorem | 70 |
| abstract_inverted_index.through | 38 |
| abstract_inverted_index.Bayesian | 80, 112 |
| abstract_inverted_index.allowing | 43 |
| abstract_inverted_index.analysis | 114 |
| abstract_inverted_index.discrete | 25 |
| abstract_inverted_index.estimate | 9, 46 |
| abstract_inverted_index.examples | 110 |
| abstract_inverted_index.stopping | 98 |
| abstract_inverted_index.algorithm | 8 |
| abstract_inverted_index.augmented | 103 |
| abstract_inverted_index.challenge | 13 |
| abstract_inverted_index.estimates | 1 |
| abstract_inverted_index.estimator | 73, 95 |
| abstract_inverted_index.formulate | 93 |
| abstract_inverted_index.gradients | 47 |
| abstract_inverted_index.inference | 81 |
| abstract_inverted_index.otherwise | 54 |
| abstract_inverted_index.parameter | 52 |
| abstract_inverted_index.problems. | 82 |
| abstract_inverted_index.proposal. | 121 |
| abstract_inverted_index.technique | 30 |
| abstract_inverted_index.Metropolis | 120 |
| abstract_inverted_index.functional | 100 |
| abstract_inverted_index.gradients? | 11 |
| abstract_inverted_index.optimizing | 116 |
| abstract_inverted_index.recoupling | 33 |
| abstract_inverted_index.assumptions | 75 |
| abstract_inverted_index.consistency | 65 |
| abstract_inverted_index.demonstrate | 106 |
| abstract_inverted_index.intractable | 2, 55 |
| abstract_inverted_index.sensitivity | 113 |
| abstract_inverted_index.contribution | 59 |
| abstract_inverted_index.expectations | 3 |
| abstract_inverted_index.information, | 91 |
| abstract_inverted_index.trajectories | 17 |
| abstract_inverted_index.accept/reject | 26 |
| abstract_inverted_index.expectations. | 56 |
| abstract_inverted_index.conventionally | 20 |
| abstract_inverted_index.differentiable | 21 |
| abstract_inverted_index.differentiates | 37 |
| abstract_inverted_index.differentiating | 6 |
| abstract_inverted_index.Metropolis-Hastings | 0, 16, 40 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 3 |
| citation_normalized_percentile |