Salvato in:
Dettagli Bibliografici
Autori principali: Angelopoulos, Anastasios N., Barber, Rina Foygel, Bates, Stephen
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2402.01139
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909211967881216
author Angelopoulos, Anastasios N.
Barber, Rina Foygel
Bates, Stephen
author_facet Angelopoulos, Anastasios N.
Barber, Rina Foygel
Bates, Stephen
contents We introduce a method for online conformal prediction with decaying step sizes. Like previous methods, ours possesses a retrospective guarantee of coverage for arbitrary sequences. However, unlike previous methods, we can simultaneously estimate a population quantile when it exists. Our theory and experiments indicate substantially improved practical properties: in particular, when the distribution is stable, the coverage is close to the desired level for every time point, not just on average over the observed sequence.
format Preprint
id arxiv_https___arxiv_org_abs_2402_01139
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Online conformal prediction with decaying step sizes
Angelopoulos, Anastasios N.
Barber, Rina Foygel
Bates, Stephen
Machine Learning
Methodology
We introduce a method for online conformal prediction with decaying step sizes. Like previous methods, ours possesses a retrospective guarantee of coverage for arbitrary sequences. However, unlike previous methods, we can simultaneously estimate a population quantile when it exists. Our theory and experiments indicate substantially improved practical properties: in particular, when the distribution is stable, the coverage is close to the desired level for every time point, not just on average over the observed sequence.
title Online conformal prediction with decaying step sizes
topic Machine Learning
Methodology
url https://arxiv.org/abs/2402.01139