Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2503.13317 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916654575779840 |
|---|---|
| author | Foglia, Enrico Bobbia, Benjamin Durasov, Nikita Bauerheim, Michael Fua, Pascal Moreau, Stephane Jardin, Thierry |
| author_facet | Foglia, Enrico Bobbia, Benjamin Durasov, Nikita Bauerheim, Michael Fua, Pascal Moreau, Stephane Jardin, Thierry |
| contents | Quantifying model uncertainty is critical for understanding prediction reliability, yet distinguishing between aleatoric and epistemic uncertainty remains challenging. We extend recent work from classification to regression to provide a novel frequentist approach to epistemic and aleatoric uncertainty estimation. We train models to generate conditional predictions by feeding their initial output back as an additional input. This method allows for a rigorous measurement of model uncertainty by observing how prediction responses change when conditioned on the model's previous answer. We provide a complete theoretical framework to analyze epistemic uncertainty in regression in a frequentist way, and explain how it can be exploited in practice to gauge a model's uncertainty, with minimal changes to the original architecture. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_13317 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Do you understand epistemic uncertainty? Think again! Rigorous frequentist epistemic uncertainty estimation in regression Foglia, Enrico Bobbia, Benjamin Durasov, Nikita Bauerheim, Michael Fua, Pascal Moreau, Stephane Jardin, Thierry Machine Learning Quantifying model uncertainty is critical for understanding prediction reliability, yet distinguishing between aleatoric and epistemic uncertainty remains challenging. We extend recent work from classification to regression to provide a novel frequentist approach to epistemic and aleatoric uncertainty estimation. We train models to generate conditional predictions by feeding their initial output back as an additional input. This method allows for a rigorous measurement of model uncertainty by observing how prediction responses change when conditioned on the model's previous answer. We provide a complete theoretical framework to analyze epistemic uncertainty in regression in a frequentist way, and explain how it can be exploited in practice to gauge a model's uncertainty, with minimal changes to the original architecture. |
| title | Do you understand epistemic uncertainty? Think again! Rigorous frequentist epistemic uncertainty estimation in regression |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2503.13317 |