BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Fast Online Changepoint Detection via Functional Pruning CUSUM sta
 tistics
DTSTART:20231003T091500Z
DTEND:20231003T101500Z
DTSTAMP:20260423T012900Z
UID:indico-event-10242@indico.math.cnrs.fr
DESCRIPTION:Speakers: Guillem Rigaill (IRAE\, LaMMe)\n\nMany modern applic
 ations of online changepoint detection require the ability to process high
 -frequency observations\, sometimes with limited available computational r
 esources. Online algorithms for detecting a change in mean often involve u
 sing a moving window\, or specifying the expected size of change. Such cho
 ices affect which changes the algorithms have most power to detect. We int
 roduce an algorithm\, Functional Online CuSUM (FOCuS)\, which is equivalen
 t to running these earlier methods simultaneously for all sizes of window\
 , or all possible values for the size of change. Our theoretical results g
 ive tight bounds on the expected computational cost per iteration of FOCuS
 \, with this being logarithmic in the number of observations. Joint work 
 with : Gaetano Romano\, Idris Eckley and Paul Fearnhead @Lancaster Univers
 ityLinks : https://arxiv.org/abs/2110.08205 or https://www.jmlr.org/papers
 /v24/21-1230.html\n\nhttps://indico.math.cnrs.fr/event/10242/
LOCATION:Salle K. Johnson\, 1er étage (1R3)
URL:https://indico.math.cnrs.fr/event/10242/
END:VEVENT
END:VCALENDAR