Automatic Miscalibration Diagnosis: Interpreting Probability Integral Transform (PIT) Histograms
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21240%2F24%3A00377379" target="_blank" >RIV/68407700:21240/24:00377379 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.14428/esann/2024.ES2024-15" target="_blank" >https://doi.org/10.14428/esann/2024.ES2024-15</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.14428/esann/2024.ES2024-15" target="_blank" >10.14428/esann/2024.ES2024-15</a>
Alternative languages
Result language
angličtina
Original language name
Automatic Miscalibration Diagnosis: Interpreting Probability Integral Transform (PIT) Histograms
Original language description
Quantifying the predictive uncertainty of a model is essential for risk assessment. We address the proper calibration of the predictive uncertainty in regression tasks by employing the probability integral transform (PIT) histogram to diagnose miscalibration. PIT histograms are often difficult to interpret, and therefore we present an approach to an automatic interpretation of PIT histograms based on an interpreter trained with a synthetic data set. Given a PIT histogram of a model and a data set, the interpreter can estimate the data-generating distribution of the data set with the main purpose of identifying the cause of miscalibration.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/EF16_019%2F0000765" target="_blank" >EF16_019/0000765: Research Center for Informatics</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach
Others
Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
ESANN 2024 proceedings
ISBN
978-2-87587-090-2
ISSN
—
e-ISSN
—
Number of pages
6
Pages from-to
137-142
Publisher name
Ciaco - i6doc.com
Place of publication
Louvain la Neuve
Event location
Bruggy
Event date
Oct 9, 2024
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—