BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Schrödinger bridge and Trajectory Inference (Part 1)
DTSTART:20230316T140000
DTEND:20230316T150000
DTSTAMP:20260408T073014Z
UID:049a8e5ee3c354a24ab145faf2b3ca59edbd393ac318e192c5bd7abb
CATEGORIES:Conferences - Seminars
DESCRIPTION:Chizat Lénaic (EPFL)  \n\nAbstract:\nWe consider statistical
  and computation methods to infer trajectories of a stochastic process fro
 m snapshots of its temporal marginals. This problem arises for instance in
  the analysis of single cell RNA-sequencing data. The goal of these lectur
 es is to present and understand the estimator proposed by [Lavenant et al.
  2020] which searches for the diffusion process that fits the observations
  with minimal entropy relative to a Wiener process. This estimator comes w
 ith consistency guarantees—for a suitable class of ground truth processe
 s—and lends itself to computational methods with global optimality guara
 ntees. Its analysis is the occasion to review important tools from entropi
 c optimal transport — aka the Schrödinger bridge problem.\n 
LOCATION:Bernoulli Center
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR