BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.4.0.1//EN
TZID:America/New_York
X-WR-TIMEZONE:America/New_York
BEGIN:VEVENT
UID:825@fds.yale.edu
DTSTART;TZID=America/New_York:20241219T100000
DTEND;TZID=America/New_York:20241219T110000
DTSTAMP:20250916T142146Z
URL:https://fds.yale.edu/events/fds-seminar-neha-wadia-flatiron-institute/
SUMMARY:FDS Seminar: Neha Wadia (Flatiron Institute)
DESCRIPTION:\n"Gibbs sampling from log-concave distributions under smoothne
 ss assumptions"\n\n\n\nAbstract: The Gibbs sampler\, also known as the coo
 rdinate hit-and-run algorithm\, is a Markov chain that is widely used to d
 raw samples from probability distributions in arbitrary dimensions. At eac
 h iteration of the algorithm\, a randomly selected coordinate is resampled
  from the distribution that results from conditioning on all the other coo
 rdinates. Although the Gibbs sampler is several decades old\, non-asymptot
 ic guarantees that identify the dimension dependence of its convergence be
 havior have only just begun to emerge. Building on the recent work of Adit
 i Laddha and Santosh Vempala\, in which they establish a mixing time bound
  for Gibbs sampling from a uniform distribution supported on a convex body
  in $\\mathbb{R}^n$ that is polynomial in $n$\, I will discuss a new mixin
 g time bound for Gibbs sampling from strongly log-concave distributions su
 pported on $\\mathbb{R}^n$ under some smoothness assumptions.\n\n\n\nBio: 
 Neha Wadia is a postdoctoral fellow at the Center for Computational Mathem
 atics of the Flatiron Institute. She holds undergraduate and masters degre
 es in physics from Amherst College and the Perimeter Institute\, respect
 ively\, and a PhD in biophysics from the University of California\, Berkel
 ey. Neha is interested in foundational problems in machine learning and th
 e theory of computing\, and in algorithmic challenges at the intersection 
 of machine learning with the natural sciences. Outside of research\, Neha 
 spends a lot of time thinking about\, reading about\, and in pursuit of go
 od food.\n
CATEGORIES:FDS Events,Postdoctoral Applicants
LOCATION:https://yale.zoom.us/j/99788429879%20
END:VEVENT
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:STANDARD
DTSTART:20241103T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
END:STANDARD
END:VTIMEZONE
END:VCALENDAR