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:20220327T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
TZNAME:EET
DTSTART:20221030T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20220707T144500
DTEND;TZID=Europe/Helsinki:20220707T153000
DTSTAMP:20260730T145417
CREATED:20220622T070435Z
LAST-MODIFIED:20220622T070435Z
UID:13808-1657205100-1657207800@crest.science
SUMMARY:Mathieu GERBER (Bristol University) " A Global Stochastic Optimization Particle Filter Algorithm"
DESCRIPTION:Statistical Seminar: \nTime: 2:45 pm -3.30pm\nDate: 07th of July 2022\nPlace: Room 3001 \nMathieu GERBER (Bristol University) ” A Global Stochastic Optimization Particle Filter Algorithm” \nAbstract:We introduce a new online algorithm for expected log-likelihood maximization in situations where the objective function is multi-modal and/or has saddle points\, that we term G-PFSO. The key element underpinning G-PFSO is a probability distribution which (a) is shown to concentrate on the target parameter value as the sample size increases and (b) can be efficiently estimated by means of a standard particle filter algorithm. This distribution depends on a learning rate\, where the faster the learning rate the quicker it concentrates on the desired element of the search space\, but the less likely G-PFSO is to escape from a local optimum of the objective function. In order to achieve a fast convergence rate with a slow learning rate\, G-PFSO exploits the acceleration property of averaging\, well-known in the stochastic gradient literature. Considering several challenging estimation problems\, the numerical experiments show that\, with high probability\, G-PFSO successfully finds the highest mode of the objective function and converges to its global maximizer at the optimal rate. While the focus of this work is expected log-likelihood\nmaximization\, the proposed methodology and its theory apply more generally for optimizing a function defined through an expectation.\n \nJoint work : Randal Douc \nOrganizers:\nCristina BUTUCEA (CREST)\, Alexandre TSYBAKOV (CREST)\, Karim LOUNICI (CMAP) \, Jaouad MOURTADA (CREST)\nSponsors:\nCREST-CMAP \n
URL:https://crest.science/event/mathieu-gerber-bristol-university-a-global-stochastic-optimization-particle-filter-algorithm/
CATEGORIES:Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR