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:20210328T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
TZNAME:EET
DTSTART:20211031T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20211115T150000
DTEND;TZID=Europe/Helsinki:20211115T161500
DTSTAMP:20260712T002348
CREATED:20211007T103457Z
LAST-MODIFIED:20211020T042216Z
UID:13037-1636988400-1636992900@crest.science
SUMMARY:Daniel HSU (Columbia University) - "Computational Lower Bounds for Tensor PCA"
DESCRIPTION:Statistical Seminar: Every Monday at 2:00 pm.\nTime: 3:00 pm – 4:15 pm exceptionally\nDate: 15th of November 2021\nPlace: visio \nDaniel HSU (Columbia University) – “Computational Lower Bounds for Tensor PCA ” \nAbstract: Tensor PCA is a model statistical inference problem introduced by Montanari and Richard in 2014 for studying method-of-moments approaches to parameter estimation in latent variable models. Unlike the matrix counterpart of the problem\, Tensor PCA exhibits a computational-statistical gap in the sample-size regime where the problem is information-theoretically solvable but no computationally-efficient algorithm is known. I will describe unconditional computational lower bounds on classes of algorithms for solving Tensor PCA that shed light on limitations of commonly-used solution approaches\, including gradient descent and power iteration\, as well as the role of overparameterization. This talk is based on joint work with Rishabh Dudeja. \n  \nOrganizers:\nCristina BUTUCEA (CREST)\, Alexandre TSYBAKOV (CREST)\, Karim LOUNICI (CMAP) \, Jaouad MOURTADA (CREST)\nSponsors:\nCREST-CMAP \n
URL:https://crest.science/event/daniel-hsu-inria-tba/
CATEGORIES:Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR