Stability of deep neural networks via discrete rough paths

Simple item page
dc.bibliographicCitation.seriesTitleWIAS Preprintseng
dc.bibliographicCitation.volume2732
dc.contributor.authorBayer, Christian
dc.contributor.authorFriz, Peter
dc.contributor.authorTapia, Nikolas
dc.date.accessioned2022-06-30T13:03:31Z
dc.date.available2022-06-30T13:03:31Z
dc.date.issued2020
dc.description.abstractUsing rough path techniques, we provide a priori estimates for the output of Deep Residual Neural Networks. In particular we derive stability bounds in terms of the total p-variation of trained weights for any p ≥ 1.eng
dc.description.versionpublishedVersioneng
dc.identifier.urihttps://oa.tib.eu/renate/handle/123456789/9382
dc.identifier.urihttps://doi.org/10.34657/8420
dc.language.isoeng
dc.publisherBerlin : Weierstraß-Institut für Angewandte Analysis und Stochastik
dc.relation.doihttps://doi.org/10.20347/WIAS.PREPRINT.2732
dc.relation.issn2198-5855
dc.rights.licenseThis document may be downloaded, read, stored and printed for your own use within the limits of § 53 UrhG but it may not be distributed via the internet or passed on to external parties.eng
dc.rights.licenseDieses Dokument darf im Rahmen von § 53 UrhG zum eigenen Gebrauch kostenfrei heruntergeladen, gelesen, gespeichert und ausgedruckt, aber nicht im Internet bereitgestellt oder an Außenstehende weitergegeben werden.ger
dc.subject.ddc510
dc.subject.otherDeep neural networkseng
dc.subject.otheriterated sums signatureeng
dc.titleStability of deep neural networks via discrete rough pathseng
dc.typeReporteng
dc.typeTexteng
dcterms.extent25 S.
tib.accessRightsopenAccess
wgl.contributorWIAS
wgl.subjectMathematik
wgl.typeReport / Forschungsbericht / Arbeitspapier
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
wias_preprints_2732.pdf
Size:
379.9 KB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Mathematik
WIAS Preprints