Online Multivalid Learning: Means, Moments, and Prediction Intervals

Simple item page
dc.citation.articleNumber82
dc.citation.journalTitle13th Innovations in Theoretical Computer Science Conference (ITCS 2022)
dc.contributor.authorGupta, Varun
dc.contributor.authorJung, Christopher
dc.contributor.authorNoarov, Georgy
dc.contributor.authorPai, Mallesh M.
dc.contributor.authorRoth, Aaron
dc.date.accessioned2022-03-24T13:31:34Z
dc.date.available2022-03-24T13:31:34Z
dc.date.issued2022
dc.description.abstractWe present a general, efficient technique for providing contextual predictions that are “multivalid” in various senses, against an online sequence of adversarially chosen examples (x, y). This means that the resulting estimates correctly predict various statistics of the labels y not just marginally –as averaged over the sequence of examples – but also conditionally on x ∈ G for any G belonging to an arbitrary intersecting collection of groups G. We provide three instantiations of this framework. The first is mean prediction, which corresponds to an online algorithm satisfying the notion of multicalibration from [5]. The second is variance and higher moment prediction, which corresponds to an online algorithm satisfying the notion of mean-conditioned moment multicalibration from [6]. Finally, we define a new notion of prediction interval multivalidity, and give an algorithm for finding prediction intervals which satisfy it. Because our algorithms handle adversarially chosen examples, they can equally well be used to predict statistics of the residuals of arbitrary point prediction methods, giving rise to very general techniques for quantifying the uncertainty of predictions of black box algorithms, even in an online adversarial setting. When instantiated for prediction intervals, this solves a similar problem as conformal prediction, but in an adversarial environment and with multivalidity guarantees stronger than simple marginal coverage guarantees.
dc.identifier.citationGupta, Varun, Jung, Christopher, Noarov, Georgy, et al.. "Online Multivalid Learning: Means, Moments, and Prediction Intervals." <i>13th Innovations in Theoretical Computer Science Conference (ITCS 2022),</i> (2022) Dagstuhl Publishing: https://doi.org/10.4230/LIPIcs.ITCS.2022.82.
dc.identifier.digitalLIPIcs-ITCS-2022-82
dc.identifier.doihttps://doi.org/10.4230/LIPIcs.ITCS.2022.82
dc.identifier.urihttps://hdl.handle.net/1911/112031
dc.language.isoeng
dc.publisherDagstuhl Publishing
dc.rightsLicensed under Creative Commons License CC-BY 4.0
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.titleOnline Multivalid Learning: Means, Moments, and Prediction Intervals
dc.typeJournal article
dc.type.dcmiText
dc.type.publicationpublisher version
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
LIPIcs-ITCS-2022-82.pdf
Size:
787.48 KB
Format:
Adobe Portable Document Format
Download
Collections
Faculty Publications
Economics Publications