BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CREST - ECPv5.1.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:CREST
X-ORIGINAL-URL:https://crest.science
X-WR-CALDESC:Events for CREST
BEGIN:VTIMEZONE
TZID:Europe/Helsinki
BEGIN:DAYLIGHT
TZOFFSETFROM:+0200
TZOFFSETTO:+0300
TZNAME:EEST
DTSTART:20230326T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
TZNAME:EET
DTSTART:20231029T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20231204T150000
DTEND;TZID=Europe/Helsinki:20231204T163000
DTSTAMP:20260710T232853
CREATED:20231129T110623Z
LAST-MODIFIED:20231129T120434Z
UID:16280-1701702000-1701707400@crest.science
SUMMARY:Anindya DE (University of Pennsylvania) - "Testing convex truncation"
DESCRIPTION:Statistical Seminar: Every Monday at 2:00 pm.\nTime: 3:00 pm – 4:00 pm\nDate: 4th December 2023\nPlace: ZOOM \n  \nAnindya De (University of Pennsylvania) “Testing convex truncation” \n Abstract: We study the basic statistical problem of testing whether normally distributed n-dimensional data has been truncated\, i.e. altered by only retaining points that lie in some unknown truncation set S. As our main algorithmic results\, (1) We give a computationally efficient O(n)-sample algorithm that can distinguish the standard normal distribution from the normal conditioned on an unknown and arbitrary convex set S. (2) We give a different computationally efficient O(n)-sample algorithm that can distinguish the standard normal distribution from the normal conditioned on an unknown and arbitrary mixture of symmetric convex sets. \nThese results stand in sharp contrast with known results for learning or testing convex bodies with respect to the normal distribution or learning convex-truncated normal distributions\, where state-of-the-art algorithms require essentially n^{O(sqrt{n})} samples. An easy argument shows that no finite number of samples suffices to distinguish the normal from an unknown and arbitrary mixture of general (not necessarily symmetric) convex sets\, so no common generalization of results (1) and (2) above is possible. We also prove lower bounds on the sample complexity of distinguishing algorithms (computationally efficient or otherwise) for various classes of convex truncations; in some cases these lower bounds match our algorithms up to logarithmic or even constant factors. \nBased on joint work with : Shivam Nadimpalli and Rocco Servedio. \nLink zoom : https://zoom.us/j/98972999889?pwd=OWI2QkdTWDJDQUgvSUN1ZGhGWV \nOrganizers: \nZCristina BUTUCEA (CREST)\, Karim LOUNICI (CMAP) \, Jaouad MOURTADA (CREST) \nSponsors:\nCREST-CMAP \n
URL:https://crest.science/event/anindya-de-university-of-pennsylvania-testing-convex-truncation/
CATEGORIES:Seminars,Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR