Universal Functional Regression with Neural Operator Flows Article Swipe
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2404.02986
Regression on function spaces is typically limited to models with Gaussian process priors. We introduce the notion of universal functional regression, in which we aim to learn a prior distribution over non-Gaussian function spaces that remains mathematically tractable for functional regression. To do this, we develop Neural Operator Flows (OpFlow), an infinite-dimensional extension of normalizing flows. OpFlow is an invertible operator that maps the (potentially unknown) data function space into a Gaussian process, allowing for exact likelihood estimation of functional point evaluations. OpFlow enables robust and accurate uncertainty quantification via drawing posterior samples of the Gaussian process and subsequently mapping them into the data function space. We empirically study the performance of OpFlow on regression and generation tasks with data generated from Gaussian processes with known posterior forms and non-Gaussian processes, as well as real-world earthquake seismograms with an unknown closed-form distribution.
Related Topics
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2404.02986
- https://arxiv.org/pdf/2404.02986
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4394019821
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4394019821Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2404.02986Digital Object Identifier
- Title
-
Universal Functional Regression with Neural Operator FlowsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-04-03Full publication date if available
- Authors
-
Yaozhong Shi, Angela F. Gao, Zachary E. Ross, Kamyar AzizzadenesheliList of authors in order
- Landing page
-
https://arxiv.org/abs/2404.02986Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2404.02986Direct 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/2404.02986Direct OA link when available
- Concepts
-
Operator (biology), Regression, Mathematics, Computer science, Statistics, Biology, Biochemistry, Transcription factor, Repressor, GeneTop 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/W4394019821 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2404.02986 |
| ids.doi | https://doi.org/10.48550/arxiv.2404.02986 |
| ids.openalex | https://openalex.org/W4394019821 |
| fwci | |
| type | preprint |
| title | Universal Functional Regression with Neural Operator Flows |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10320 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9135000109672546 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Neural Networks and Applications |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C17020691 |
| concepts[0].level | 5 |
| concepts[0].score | 0.6098754405975342 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q139677 |
| concepts[0].display_name | Operator (biology) |
| concepts[1].id | https://openalex.org/C83546350 |
| concepts[1].level | 2 |
| concepts[1].score | 0.5960738658905029 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q1139051 |
| concepts[1].display_name | Regression |
| concepts[2].id | https://openalex.org/C33923547 |
| concepts[2].level | 0 |
| concepts[2].score | 0.41982612013816833 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[2].display_name | Mathematics |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.37855982780456543 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C105795698 |
| concepts[4].level | 1 |
| concepts[4].score | 0.24679988622665405 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q12483 |
| concepts[4].display_name | Statistics |
| concepts[5].id | https://openalex.org/C86803240 |
| concepts[5].level | 0 |
| concepts[5].score | 0.15523460507392883 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q420 |
| concepts[5].display_name | Biology |
| concepts[6].id | https://openalex.org/C55493867 |
| concepts[6].level | 1 |
| concepts[6].score | 0.0 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q7094 |
| concepts[6].display_name | Biochemistry |
| concepts[7].id | https://openalex.org/C86339819 |
| concepts[7].level | 3 |
| concepts[7].score | 0.0 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q407384 |
| concepts[7].display_name | Transcription factor |
| concepts[8].id | https://openalex.org/C158448853 |
| concepts[8].level | 4 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q425218 |
| concepts[8].display_name | Repressor |
| concepts[9].id | https://openalex.org/C104317684 |
| concepts[9].level | 2 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q7187 |
| concepts[9].display_name | Gene |
| keywords[0].id | https://openalex.org/keywords/operator |
| keywords[0].score | 0.6098754405975342 |
| keywords[0].display_name | Operator (biology) |
| keywords[1].id | https://openalex.org/keywords/regression |
| keywords[1].score | 0.5960738658905029 |
| keywords[1].display_name | Regression |
| keywords[2].id | https://openalex.org/keywords/mathematics |
| keywords[2].score | 0.41982612013816833 |
| keywords[2].display_name | Mathematics |
| keywords[3].id | https://openalex.org/keywords/computer-science |
| keywords[3].score | 0.37855982780456543 |
| keywords[3].display_name | Computer science |
| keywords[4].id | https://openalex.org/keywords/statistics |
| keywords[4].score | 0.24679988622665405 |
| keywords[4].display_name | Statistics |
| keywords[5].id | https://openalex.org/keywords/biology |
| keywords[5].score | 0.15523460507392883 |
| keywords[5].display_name | Biology |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2404.02986 |
| 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/2404.02986 |
| 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/2404.02986 |
| locations[1].id | doi:10.48550/arxiv.2404.02986 |
| 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.2404.02986 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5100528508 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Yaozhong Shi |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Shi, Yaozhong |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5024997075 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-8574-8728 |
| authorships[1].author.display_name | Angela F. Gao |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Gao, Angela F. |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5006827123 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-6343-8400 |
| authorships[2].author.display_name | Zachary E. Ross |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Ross, Zachary E. |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5038884528 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-8507-1868 |
| authorships[3].author.display_name | Kamyar Azizzadenesheli |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Azizzadenesheli, Kamyar |
| authorships[3].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/2404.02986 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Universal Functional Regression with Neural Operator Flows |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10320 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9135000109672546 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Neural Networks and Applications |
| related_works | https://openalex.org/W2748952813, https://openalex.org/W4391375266, https://openalex.org/W1979597421, https://openalex.org/W2007980826, https://openalex.org/W2061531152, https://openalex.org/W3002753104, https://openalex.org/W2077600819, https://openalex.org/W2142036596, https://openalex.org/W2072657027, https://openalex.org/W2600246793 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2404.02986 |
| 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/2404.02986 |
| 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/2404.02986 |
| primary_location.id | pmh:oai:arXiv.org:2404.02986 |
| 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/2404.02986 |
| 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/2404.02986 |
| publication_date | 2024-04-03 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 27, 70 |
| abstract_inverted_index.To | 41 |
| abstract_inverted_index.We | 13, 106 |
| abstract_inverted_index.an | 50, 58, 138 |
| abstract_inverted_index.as | 131, 133 |
| abstract_inverted_index.do | 42 |
| abstract_inverted_index.in | 21 |
| abstract_inverted_index.is | 4, 57 |
| abstract_inverted_index.of | 17, 53, 78, 93, 111 |
| abstract_inverted_index.on | 1, 113 |
| abstract_inverted_index.to | 7, 25 |
| abstract_inverted_index.we | 23, 44 |
| abstract_inverted_index.aim | 24 |
| abstract_inverted_index.and | 85, 97, 115, 128 |
| abstract_inverted_index.for | 38, 74 |
| abstract_inverted_index.the | 15, 63, 94, 102, 109 |
| abstract_inverted_index.via | 89 |
| abstract_inverted_index.data | 66, 103, 119 |
| abstract_inverted_index.from | 121 |
| abstract_inverted_index.into | 69, 101 |
| abstract_inverted_index.maps | 62 |
| abstract_inverted_index.over | 30 |
| abstract_inverted_index.that | 34, 61 |
| abstract_inverted_index.them | 100 |
| abstract_inverted_index.well | 132 |
| abstract_inverted_index.with | 9, 118, 124, 137 |
| abstract_inverted_index.Flows | 48 |
| abstract_inverted_index.exact | 75 |
| abstract_inverted_index.forms | 127 |
| abstract_inverted_index.known | 125 |
| abstract_inverted_index.learn | 26 |
| abstract_inverted_index.point | 80 |
| abstract_inverted_index.prior | 28 |
| abstract_inverted_index.space | 68 |
| abstract_inverted_index.study | 108 |
| abstract_inverted_index.tasks | 117 |
| abstract_inverted_index.this, | 43 |
| abstract_inverted_index.which | 22 |
| abstract_inverted_index.Neural | 46 |
| abstract_inverted_index.OpFlow | 56, 82, 112 |
| abstract_inverted_index.flows. | 55 |
| abstract_inverted_index.models | 8 |
| abstract_inverted_index.notion | 16 |
| abstract_inverted_index.robust | 84 |
| abstract_inverted_index.space. | 105 |
| abstract_inverted_index.spaces | 3, 33 |
| abstract_inverted_index.develop | 45 |
| abstract_inverted_index.drawing | 90 |
| abstract_inverted_index.enables | 83 |
| abstract_inverted_index.limited | 6 |
| abstract_inverted_index.mapping | 99 |
| abstract_inverted_index.priors. | 12 |
| abstract_inverted_index.process | 11, 96 |
| abstract_inverted_index.remains | 35 |
| abstract_inverted_index.samples | 92 |
| abstract_inverted_index.unknown | 139 |
| abstract_inverted_index.Gaussian | 10, 71, 95, 122 |
| abstract_inverted_index.Operator | 47 |
| abstract_inverted_index.accurate | 86 |
| abstract_inverted_index.allowing | 73 |
| abstract_inverted_index.function | 2, 32, 67, 104 |
| abstract_inverted_index.operator | 60 |
| abstract_inverted_index.process, | 72 |
| abstract_inverted_index.unknown) | 65 |
| abstract_inverted_index.(OpFlow), | 49 |
| abstract_inverted_index.extension | 52 |
| abstract_inverted_index.generated | 120 |
| abstract_inverted_index.introduce | 14 |
| abstract_inverted_index.posterior | 91, 126 |
| abstract_inverted_index.processes | 123 |
| abstract_inverted_index.tractable | 37 |
| abstract_inverted_index.typically | 5 |
| abstract_inverted_index.universal | 18 |
| abstract_inverted_index.Regression | 0 |
| abstract_inverted_index.earthquake | 135 |
| abstract_inverted_index.estimation | 77 |
| abstract_inverted_index.functional | 19, 39, 79 |
| abstract_inverted_index.generation | 116 |
| abstract_inverted_index.invertible | 59 |
| abstract_inverted_index.likelihood | 76 |
| abstract_inverted_index.processes, | 130 |
| abstract_inverted_index.real-world | 134 |
| abstract_inverted_index.regression | 114 |
| abstract_inverted_index.closed-form | 140 |
| abstract_inverted_index.empirically | 107 |
| abstract_inverted_index.normalizing | 54 |
| abstract_inverted_index.performance | 110 |
| abstract_inverted_index.regression, | 20 |
| abstract_inverted_index.regression. | 40 |
| abstract_inverted_index.seismograms | 136 |
| abstract_inverted_index.uncertainty | 87 |
| abstract_inverted_index.(potentially | 64 |
| abstract_inverted_index.distribution | 29 |
| abstract_inverted_index.evaluations. | 81 |
| abstract_inverted_index.non-Gaussian | 31, 129 |
| abstract_inverted_index.subsequently | 98 |
| abstract_inverted_index.distribution. | 141 |
| abstract_inverted_index.mathematically | 36 |
| abstract_inverted_index.quantification | 88 |
| abstract_inverted_index.infinite-dimensional | 51 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile |