Uncertainty Quantification for Deep Learning Article Swipe
Peter Jan van Leeuwen
,
J. Christine Chiu
,
C. Kevin Yang
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2405.20550
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2405.20550
We present a critical survey on the consistency of uncertainty quantification used in deep learning and highlight partial uncertainty coverage and many inconsistencies. We then provide a comprehensive and statistically consistent framework for uncertainty quantification in deep learning that accounts for all major sources of uncertainty: input data, training and testing data, neural network weights, and machine-learning model imperfections, targeting regression problems. We systematically quantify each source by applying Bayes' theorem and conditional probability densities and introduce a fast, practical implementation method. We demonstrate its effectiveness on a simple regression problem and a real-world application: predicting cloud autoconversion rates using a neural network trained on aircraft measurements from the Azores and guided by a two-moment bin model of the stochastic collection equation. In this application, uncertainty from the training and testing data dominates, followed by input data, neural network model, and weight variability. Finally, we highlight the practical advantages of this methodology, showing that explicitly modeling training data uncertainty improves robustness to new inputs that fall outside the training data, and enhances model reliability in real-world scenarios.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2405.20550
- https://arxiv.org/pdf/2405.20550
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4399317170
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4399317170Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2405.20550Digital Object Identifier
- Title
-
Uncertainty Quantification for Deep LearningWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-05-31Full publication date if available
- Authors
-
Peter Jan van Leeuwen, J. Christine Chiu, C. Kevin YangList of authors in order
- Landing page
-
https://arxiv.org/abs/2405.20550Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2405.20550Direct 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/2405.20550Direct OA link when available
- Concepts
-
Deep learning, Uncertainty quantification, Artificial intelligence, Computer science, Data science, Machine learningTop 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/W4399317170 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2405.20550 |
| ids.doi | https://doi.org/10.48550/arxiv.2405.20550 |
| ids.openalex | https://openalex.org/W4399317170 |
| fwci | |
| type | preprint |
| title | Uncertainty Quantification for Deep Learning |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10876 |
| topics[0].field.id | https://openalex.org/fields/22 |
| topics[0].field.display_name | Engineering |
| topics[0].score | 0.6601999998092651 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2207 |
| topics[0].subfield.display_name | Control and Systems Engineering |
| topics[0].display_name | Fault Detection and Control Systems |
| topics[1].id | https://openalex.org/T12560 |
| topics[1].field.id | https://openalex.org/fields/22 |
| topics[1].field.display_name | Engineering |
| topics[1].score | 0.6258999705314636 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2202 |
| topics[1].subfield.display_name | Aerospace Engineering |
| topics[1].display_name | Nuclear Engineering Thermal-Hydraulics |
| topics[2].id | https://openalex.org/T10928 |
| topics[2].field.id | https://openalex.org/fields/18 |
| topics[2].field.display_name | Decision Sciences |
| topics[2].score | 0.6079999804496765 |
| topics[2].domain.id | https://openalex.org/domains/2 |
| topics[2].domain.display_name | Social Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1804 |
| topics[2].subfield.display_name | Statistics, Probability and Uncertainty |
| topics[2].display_name | Probabilistic and Robust Engineering Design |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C108583219 |
| concepts[0].level | 2 |
| concepts[0].score | 0.4924796521663666 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[0].display_name | Deep learning |
| concepts[1].id | https://openalex.org/C32230216 |
| concepts[1].level | 2 |
| concepts[1].score | 0.47196710109710693 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q7882499 |
| concepts[1].display_name | Uncertainty quantification |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.4451012909412384 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.42523786425590515 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C2522767166 |
| concepts[4].level | 1 |
| concepts[4].score | 0.325090229511261 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q2374463 |
| concepts[4].display_name | Data science |
| concepts[5].id | https://openalex.org/C119857082 |
| concepts[5].level | 1 |
| concepts[5].score | 0.2734665870666504 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[5].display_name | Machine learning |
| keywords[0].id | https://openalex.org/keywords/deep-learning |
| keywords[0].score | 0.4924796521663666 |
| keywords[0].display_name | Deep learning |
| keywords[1].id | https://openalex.org/keywords/uncertainty-quantification |
| keywords[1].score | 0.47196710109710693 |
| keywords[1].display_name | Uncertainty quantification |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.4451012909412384 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/computer-science |
| keywords[3].score | 0.42523786425590515 |
| keywords[3].display_name | Computer science |
| keywords[4].id | https://openalex.org/keywords/data-science |
| keywords[4].score | 0.325090229511261 |
| keywords[4].display_name | Data science |
| keywords[5].id | https://openalex.org/keywords/machine-learning |
| keywords[5].score | 0.2734665870666504 |
| keywords[5].display_name | Machine learning |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2405.20550 |
| 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/2405.20550 |
| 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/2405.20550 |
| locations[1].id | doi:10.48550/arxiv.2405.20550 |
| 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.2405.20550 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5063378345 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-2325-5340 |
| authorships[0].author.display_name | Peter Jan van Leeuwen |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | van Leeuwen, Peter Jan |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5034922132 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-8951-6913 |
| authorships[1].author.display_name | J. Christine Chiu |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Chiu, J. Christine |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5102757639 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-7685-4481 |
| authorships[2].author.display_name | C. Kevin Yang |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Yang, C. Kevin |
| 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/2405.20550 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Uncertainty Quantification for Deep Learning |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-19T23:35:23.961156 |
| primary_topic.id | https://openalex.org/T10876 |
| primary_topic.field.id | https://openalex.org/fields/22 |
| primary_topic.field.display_name | Engineering |
| primary_topic.score | 0.6601999998092651 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2207 |
| primary_topic.subfield.display_name | Control and Systems Engineering |
| primary_topic.display_name | Fault Detection and Control Systems |
| related_works | https://openalex.org/W2731899572, https://openalex.org/W3215138031, https://openalex.org/W3009238340, https://openalex.org/W4321369474, https://openalex.org/W4360585206, https://openalex.org/W4285208911, https://openalex.org/W3082895349, https://openalex.org/W4213079790, https://openalex.org/W2248239756, https://openalex.org/W4323565446 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2405.20550 |
| 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/2405.20550 |
| 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/2405.20550 |
| primary_location.id | pmh:oai:arXiv.org:2405.20550 |
| 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/2405.20550 |
| 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/2405.20550 |
| publication_date | 2024-05-31 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 2, 26, 77, 87, 92, 100, 113 |
| abstract_inverted_index.In | 122 |
| abstract_inverted_index.We | 0, 23, 62, 82 |
| abstract_inverted_index.by | 67, 112, 134 |
| abstract_inverted_index.in | 12, 35, 174 |
| abstract_inverted_index.of | 8, 44, 117, 149 |
| abstract_inverted_index.on | 5, 86, 104 |
| abstract_inverted_index.to | 161 |
| abstract_inverted_index.we | 144 |
| abstract_inverted_index.all | 41 |
| abstract_inverted_index.and | 15, 20, 28, 49, 55, 71, 75, 91, 110, 129, 140, 170 |
| abstract_inverted_index.bin | 115 |
| abstract_inverted_index.for | 32, 40 |
| abstract_inverted_index.its | 84 |
| abstract_inverted_index.new | 162 |
| abstract_inverted_index.the | 6, 108, 118, 127, 146, 167 |
| abstract_inverted_index.data | 131, 157 |
| abstract_inverted_index.deep | 13, 36 |
| abstract_inverted_index.each | 65 |
| abstract_inverted_index.fall | 165 |
| abstract_inverted_index.from | 107, 126 |
| abstract_inverted_index.many | 21 |
| abstract_inverted_index.that | 38, 153, 164 |
| abstract_inverted_index.then | 24 |
| abstract_inverted_index.this | 123, 150 |
| abstract_inverted_index.used | 11 |
| abstract_inverted_index.cloud | 96 |
| abstract_inverted_index.data, | 47, 51, 136, 169 |
| abstract_inverted_index.fast, | 78 |
| abstract_inverted_index.input | 46, 135 |
| abstract_inverted_index.major | 42 |
| abstract_inverted_index.model | 57, 116, 172 |
| abstract_inverted_index.rates | 98 |
| abstract_inverted_index.using | 99 |
| abstract_inverted_index.Azores | 109 |
| abstract_inverted_index.Bayes' | 69 |
| abstract_inverted_index.guided | 111 |
| abstract_inverted_index.inputs | 163 |
| abstract_inverted_index.model, | 139 |
| abstract_inverted_index.neural | 52, 101, 137 |
| abstract_inverted_index.simple | 88 |
| abstract_inverted_index.source | 66 |
| abstract_inverted_index.survey | 4 |
| abstract_inverted_index.weight | 141 |
| abstract_inverted_index.method. | 81 |
| abstract_inverted_index.network | 53, 102, 138 |
| abstract_inverted_index.outside | 166 |
| abstract_inverted_index.partial | 17 |
| abstract_inverted_index.present | 1 |
| abstract_inverted_index.problem | 90 |
| abstract_inverted_index.provide | 25 |
| abstract_inverted_index.showing | 152 |
| abstract_inverted_index.sources | 43 |
| abstract_inverted_index.testing | 50, 130 |
| abstract_inverted_index.theorem | 70 |
| abstract_inverted_index.trained | 103 |
| abstract_inverted_index.Finally, | 143 |
| abstract_inverted_index.accounts | 39 |
| abstract_inverted_index.aircraft | 105 |
| abstract_inverted_index.applying | 68 |
| abstract_inverted_index.coverage | 19 |
| abstract_inverted_index.critical | 3 |
| abstract_inverted_index.enhances | 171 |
| abstract_inverted_index.followed | 133 |
| abstract_inverted_index.improves | 159 |
| abstract_inverted_index.learning | 14, 37 |
| abstract_inverted_index.modeling | 155 |
| abstract_inverted_index.quantify | 64 |
| abstract_inverted_index.training | 48, 128, 156, 168 |
| abstract_inverted_index.weights, | 54 |
| abstract_inverted_index.densities | 74 |
| abstract_inverted_index.equation. | 121 |
| abstract_inverted_index.framework | 31 |
| abstract_inverted_index.highlight | 16, 145 |
| abstract_inverted_index.introduce | 76 |
| abstract_inverted_index.practical | 79, 147 |
| abstract_inverted_index.problems. | 61 |
| abstract_inverted_index.targeting | 59 |
| abstract_inverted_index.advantages | 148 |
| abstract_inverted_index.collection | 120 |
| abstract_inverted_index.consistent | 30 |
| abstract_inverted_index.dominates, | 132 |
| abstract_inverted_index.explicitly | 154 |
| abstract_inverted_index.predicting | 95 |
| abstract_inverted_index.real-world | 93, 175 |
| abstract_inverted_index.regression | 60, 89 |
| abstract_inverted_index.robustness | 160 |
| abstract_inverted_index.scenarios. | 176 |
| abstract_inverted_index.stochastic | 119 |
| abstract_inverted_index.two-moment | 114 |
| abstract_inverted_index.conditional | 72 |
| abstract_inverted_index.consistency | 7 |
| abstract_inverted_index.demonstrate | 83 |
| abstract_inverted_index.probability | 73 |
| abstract_inverted_index.reliability | 173 |
| abstract_inverted_index.uncertainty | 9, 18, 33, 125, 158 |
| abstract_inverted_index.application, | 124 |
| abstract_inverted_index.application: | 94 |
| abstract_inverted_index.measurements | 106 |
| abstract_inverted_index.methodology, | 151 |
| abstract_inverted_index.uncertainty: | 45 |
| abstract_inverted_index.variability. | 142 |
| abstract_inverted_index.comprehensive | 27 |
| abstract_inverted_index.effectiveness | 85 |
| abstract_inverted_index.statistically | 29 |
| abstract_inverted_index.autoconversion | 97 |
| abstract_inverted_index.imperfections, | 58 |
| abstract_inverted_index.implementation | 80 |
| abstract_inverted_index.quantification | 10, 34 |
| abstract_inverted_index.systematically | 63 |
| abstract_inverted_index.inconsistencies. | 22 |
| abstract_inverted_index.machine-learning | 56 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 3 |
| citation_normalized_percentile |