BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Andrew Duncan (Imperial College London)
DTSTART:20200825T120000Z
DTEND:20200825T130000Z
DTSTAMP:20260423T034448Z
UID:DSCSS/8
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/DSCSS/8/">On
  the geometry of Stein variational gradient descent</a>\nby Andrew Duncan 
 (Imperial College London) as part of Data Science and Computational Statis
 tics Seminar\n\n\nAbstract\nBayesian inference problems require sampling o
 r approximating high-dimensional probability distributions. The focus of t
 his talk is on the recently introduced Stein variational gradient descent 
 methodology\, a class of algorithms that rely on iterated steepest descent
  steps with respect to a reproducing kernel Hilbert space norm. This const
 ruction leads to interacting particle systems\, the mean-field limit of wh
 ich is a gradient flow on the space of probability distributions equipped 
 with a certain geometrical structure. We leverage this viewpoint to shed s
 ome light on the convergence properties of the algorithm\, in particular a
 ddressing the problem of choosing a suitable positive definite kernel func
 tion. Our analysis leads us to considering certain singular kernels with a
 djusted tails. This is joint work with N. Nusken (U. of Potsdam) and L. Sz
 pruch (U. Edinburgh).\n
LOCATION:https://researchseminars.org/talk/DSCSS/8/
END:VEVENT
END:VCALENDAR