PostHoc FREE Calibrating on Kolmogorov Arnold Networks Article Swipe
Wenhao Liang
,
Wei Emma Zhang
,
Yue Lin
,
Miao Xu
,
Olaf Maennel
,
Weitong Chen
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2503.01195
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2503.01195
Kolmogorov Arnold Networks (KANs) are neural architectures inspired by the Kolmogorov Arnold representation theorem that leverage B Spline parameterizations for flexible, locally adaptive function approximation. Although KANs can capture complex nonlinearities beyond those modeled by standard MultiLayer Perceptrons (MLPs), they frequently exhibit miscalibrated confidence estimates manifesting as overconfidence in dense data regions and underconfidence in sparse areas. In this work, we systematically examine the impact of four critical hyperparameters including Layer Width, Grid Order, Shortcut Function, and Grid Range on the calibration of KANs. Furthermore, we introduce a novel TemperatureScaled Loss (TSL) that integrates a temperature parameter directly into the training objective, dynamically adjusting the predictive distribution during learning. Both theoretical analysis and extensive empirical evaluations on standard benchmarks demonstrate that TSL significantly reduces calibration errors, thereby improving the reliability of probabilistic predictions. Overall, our study provides actionable insights into the design of spline based neural networks and establishes TSL as a robust loss solution for enhancing calibration.
Related Topics
Concepts
No concepts available.
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2503.01195
- https://arxiv.org/pdf/2503.01195
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W4415084349
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4415084349Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2503.01195Digital Object Identifier
- Title
-
PostHoc FREE Calibrating on Kolmogorov Arnold NetworksWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-03-03Full publication date if available
- Authors
-
Wenhao Liang, Wei Emma Zhang, Yue Lin, Miao Xu, Olaf Maennel, Weitong ChenList of authors in order
- Landing page
-
https://arxiv.org/abs/2503.01195Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2503.01195Direct 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/2503.01195Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W4415084349 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2503.01195 |
| ids.doi | https://doi.org/10.48550/arxiv.2503.01195 |
| ids.openalex | https://openalex.org/W4415084349 |
| fwci | |
| type | preprint |
| title | PostHoc FREE Calibrating on Kolmogorov Arnold Networks |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10711 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9580000042915344 |
| 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 | Target Tracking and Data Fusion in Sensor Networks |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2503.01195 |
| 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/2503.01195 |
| 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/2503.01195 |
| locations[1].id | doi:10.48550/arxiv.2503.01195 |
| 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.2503.01195 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5034165912 |
| authorships[0].author.orcid | https://orcid.org/0009-0001-2817-7719 |
| authorships[0].author.display_name | Wenhao Liang |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Liang, Wenhao |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5070697660 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-0406-5974 |
| authorships[1].author.display_name | Wei Emma Zhang |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Zhang, Wei Emma |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5101069383 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Yue Lin |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Yue, Lin |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5045898757 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-3155-8512 |
| authorships[3].author.display_name | Miao Xu |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Xu, Miao |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5006000047 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-9621-0787 |
| authorships[4].author.display_name | Olaf Maennel |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Maennel, Olaf |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5053697754 |
| authorships[5].author.orcid | |
| authorships[5].author.display_name | Weitong Chen |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Chen, Weitong |
| authorships[5].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/2503.01195 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-12T00:00:00 |
| display_name | PostHoc FREE Calibrating on Kolmogorov Arnold Networks |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10711 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9580000042915344 |
| 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 | Target Tracking and Data Fusion in Sensor Networks |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2503.01195 |
| 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/2503.01195 |
| 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/2503.01195 |
| primary_location.id | pmh:oai:arXiv.org:2503.01195 |
| 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/2503.01195 |
| 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/2503.01195 |
| publication_date | 2025-03-03 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.B | 16 |
| abstract_inverted_index.a | 87, 94, 151 |
| abstract_inverted_index.In | 57 |
| abstract_inverted_index.as | 46, 150 |
| abstract_inverted_index.by | 8, 34 |
| abstract_inverted_index.in | 48, 54 |
| abstract_inverted_index.of | 65, 82, 130, 142 |
| abstract_inverted_index.on | 79, 116 |
| abstract_inverted_index.we | 60, 85 |
| abstract_inverted_index.TSL | 121, 149 |
| abstract_inverted_index.and | 52, 76, 112, 147 |
| abstract_inverted_index.are | 4 |
| abstract_inverted_index.can | 27 |
| abstract_inverted_index.for | 19, 155 |
| abstract_inverted_index.our | 134 |
| abstract_inverted_index.the | 9, 63, 80, 99, 104, 128, 140 |
| abstract_inverted_index.Both | 109 |
| abstract_inverted_index.Grid | 72, 77 |
| abstract_inverted_index.KANs | 26 |
| abstract_inverted_index.Loss | 90 |
| abstract_inverted_index.data | 50 |
| abstract_inverted_index.four | 66 |
| abstract_inverted_index.into | 98, 139 |
| abstract_inverted_index.loss | 153 |
| abstract_inverted_index.that | 14, 92, 120 |
| abstract_inverted_index.they | 39 |
| abstract_inverted_index.this | 58 |
| abstract_inverted_index.(TSL) | 91 |
| abstract_inverted_index.KANs. | 83 |
| abstract_inverted_index.Layer | 70 |
| abstract_inverted_index.Range | 78 |
| abstract_inverted_index.based | 144 |
| abstract_inverted_index.dense | 49 |
| abstract_inverted_index.novel | 88 |
| abstract_inverted_index.study | 135 |
| abstract_inverted_index.those | 32 |
| abstract_inverted_index.work, | 59 |
| abstract_inverted_index.(KANs) | 3 |
| abstract_inverted_index.Arnold | 1, 11 |
| abstract_inverted_index.Order, | 73 |
| abstract_inverted_index.Spline | 17 |
| abstract_inverted_index.Width, | 71 |
| abstract_inverted_index.areas. | 56 |
| abstract_inverted_index.beyond | 31 |
| abstract_inverted_index.design | 141 |
| abstract_inverted_index.during | 107 |
| abstract_inverted_index.impact | 64 |
| abstract_inverted_index.neural | 5, 145 |
| abstract_inverted_index.robust | 152 |
| abstract_inverted_index.sparse | 55 |
| abstract_inverted_index.spline | 143 |
| abstract_inverted_index.(MLPs), | 38 |
| abstract_inverted_index.capture | 28 |
| abstract_inverted_index.complex | 29 |
| abstract_inverted_index.errors, | 125 |
| abstract_inverted_index.examine | 62 |
| abstract_inverted_index.exhibit | 41 |
| abstract_inverted_index.locally | 21 |
| abstract_inverted_index.modeled | 33 |
| abstract_inverted_index.reduces | 123 |
| abstract_inverted_index.regions | 51 |
| abstract_inverted_index.theorem | 13 |
| abstract_inverted_index.thereby | 126 |
| abstract_inverted_index.Although | 25 |
| abstract_inverted_index.Networks | 2 |
| abstract_inverted_index.Overall, | 133 |
| abstract_inverted_index.Shortcut | 74 |
| abstract_inverted_index.adaptive | 22 |
| abstract_inverted_index.analysis | 111 |
| abstract_inverted_index.critical | 67 |
| abstract_inverted_index.directly | 97 |
| abstract_inverted_index.function | 23 |
| abstract_inverted_index.insights | 138 |
| abstract_inverted_index.inspired | 7 |
| abstract_inverted_index.leverage | 15 |
| abstract_inverted_index.networks | 146 |
| abstract_inverted_index.provides | 136 |
| abstract_inverted_index.solution | 154 |
| abstract_inverted_index.standard | 35, 117 |
| abstract_inverted_index.training | 100 |
| abstract_inverted_index.Function, | 75 |
| abstract_inverted_index.adjusting | 103 |
| abstract_inverted_index.empirical | 114 |
| abstract_inverted_index.enhancing | 156 |
| abstract_inverted_index.estimates | 44 |
| abstract_inverted_index.extensive | 113 |
| abstract_inverted_index.flexible, | 20 |
| abstract_inverted_index.improving | 127 |
| abstract_inverted_index.including | 69 |
| abstract_inverted_index.introduce | 86 |
| abstract_inverted_index.learning. | 108 |
| abstract_inverted_index.parameter | 96 |
| abstract_inverted_index.Kolmogorov | 0, 10 |
| abstract_inverted_index.MultiLayer | 36 |
| abstract_inverted_index.actionable | 137 |
| abstract_inverted_index.benchmarks | 118 |
| abstract_inverted_index.confidence | 43 |
| abstract_inverted_index.frequently | 40 |
| abstract_inverted_index.integrates | 93 |
| abstract_inverted_index.objective, | 101 |
| abstract_inverted_index.predictive | 105 |
| abstract_inverted_index.Perceptrons | 37 |
| abstract_inverted_index.calibration | 81, 124 |
| abstract_inverted_index.demonstrate | 119 |
| abstract_inverted_index.dynamically | 102 |
| abstract_inverted_index.establishes | 148 |
| abstract_inverted_index.evaluations | 115 |
| abstract_inverted_index.manifesting | 45 |
| abstract_inverted_index.reliability | 129 |
| abstract_inverted_index.temperature | 95 |
| abstract_inverted_index.theoretical | 110 |
| abstract_inverted_index.Furthermore, | 84 |
| abstract_inverted_index.calibration. | 157 |
| abstract_inverted_index.distribution | 106 |
| abstract_inverted_index.predictions. | 132 |
| abstract_inverted_index.architectures | 6 |
| abstract_inverted_index.miscalibrated | 42 |
| abstract_inverted_index.probabilistic | 131 |
| abstract_inverted_index.significantly | 122 |
| abstract_inverted_index.approximation. | 24 |
| abstract_inverted_index.nonlinearities | 30 |
| abstract_inverted_index.overconfidence | 47 |
| abstract_inverted_index.representation | 12 |
| abstract_inverted_index.systematically | 61 |
| abstract_inverted_index.hyperparameters | 68 |
| abstract_inverted_index.underconfidence | 53 |
| abstract_inverted_index.TemperatureScaled | 89 |
| abstract_inverted_index.parameterizations | 18 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 6 |
| citation_normalized_percentile |