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:20240209T150000
DTEND;TZID=Europe/Helsinki:20240209T170000
DTSTAMP:20260711T160221
CREATED:20240205T124414Z
LAST-MODIFIED:20240205T124425Z
UID:16619-1707490800-1707498000@crest.science
SUMMARY:Online Seminar on the Interactions between Statistics and Geometry
DESCRIPTION:For thesecond meeting of the Online Seminar on the Interactions between Statistics and Geometry.\, it is a great privilege to receive Professor Santosh Vempala on the topic of High-dimensional Sampling. \nSpeaker: Santosh Vempala (Georgia Tech) \nTitle: High-dimensional Sampling: from Euclid to Riemann \nAbstract: Sampling high-dimensional densities is a basic algorithmic problem that has led to mathematically interesting tools and techniques. Many sampling algorithms can be viewed as discretizations of suitable continuous stochastic processes\, raising the questions: Which stochastic process to use? And how to discretize it? In this talk\, we discuss the use of Riemannian metrics to guide sampling algorithms and how\, perhaps surprisingly\, they can lead to improvements even for Euclidean sampling.  We will focus on two methods — Riemannian Langevin and Riemannian Hamiltonian Monte Carlo — and highlight some open questions. \nDate: February 9 \nTime: 3pm CET (9am EST\, 10pm JST\, 4pm MSK) \nZoom Link: https://us06web.zoom.us/j/2789300692?pwd=ZVAzeXRIZUREcEdlYWVPR1F5ejZOQT09 \nBest regards\, \nThe organisers (V.-E. Brunel\, A. Stromme\, A. Kroshnin\, Q. Paris) \n
URL:https://crest.science/event/online-seminar-on-the-interactions-between-statistics-and-geometry-2/
CATEGORIES:Conferences and Workshops,Statistics
END:VEVENT
END:VCALENDAR