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:20240331T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
TZNAME:EET
DTSTART:20241027T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20240527T140000
DTEND;TZID=Europe/Helsinki:20240527T151500
DTSTAMP:20260710T175121
CREATED:20240522T142613Z
LAST-MODIFIED:20240522T142834Z
UID:17047-1716818400-1716822900@crest.science
SUMMARY:Nicolas Schreuder (CNRS\, Université Gustave Eiffel) - Efficient estimation of kernel mean embeddings
DESCRIPTION:Statistical Seminar: Every Monday at 2:00 pm.\nTime: 2:00 pm – 3:15 pm\nDate: 27th May 2024\nPlace: Room 3001 \n  \nNicolas Schreuder (CNRS\, Université Gustave Eiffel) – Efficient estimation of kernel mean embeddings \n  \nAbstract: \nKernel mean embeddings are a powerful tool to represent probability distributions over arbitrary spaces as single points in a Hilbert space. Yet\, the cost of computing and storing such embeddings prohibits their direct use in large-scale settings. We propose an efficient approximation procedure based on the Nyström method\, which exploits a small random subset of the dataset. Our main result is an upper bound on the approximation error of this procedure for different sub-sampling strategies. We discuss applications of this result for numerical integration and approximation of the maximum mean discrepancy. \n  \nThe talk is based on the works : \n– A. Chatalic\, N. Schreuder\, A. Rudi\, L. Rosasco (2022). Nyström Kernel Mean Embeddings. ICML 2022. [PMLR 162:3006-3024]\n– A. Chatalic\, N. Schreuder\, E. De Vito\, L. Rosasco (2023). Efficient Numerical Integration in Reproducing Kernel Hilbert Spaces via Leverage Scores Sampling. [arXiv:2311.13548]\n  \nOrganizers:\nAnna KORBA (CREST)\, Karim LOUNICI (CMAP) \, Jaouad MOURTADA (CREST)\nSponsors:\nCREST-CMAP \n
URL:https://crest.science/event/nicolas-schreuder-cnrs-universite-gustave-eiffel-efficient-estimation-of-kernel-mean-embeddings/
CATEGORIES:Seminars,Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR