BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Schrödinger bridge and Trajectory Inference  (Part 2)
DTSTART:20230315T160000
DTEND:20230315T170000
DTSTAMP:20260406T073438Z
UID:163e4eb921a3bc70de0443dae4df7bec2907a103d68e6b436747fc7a
CATEGORIES:Conferences - Seminars
DESCRIPTION:Chizat Lénaic (EPFL) \nAbstract:   \nWe consider statisti
 cal and computation methods to infer trajectories of a stochastic process 
 from snapshots of its temporal marginals. This problem arises for instance
  in the analysis of single cell RNA-sequencing data. The goal of these lec
 tures is to present and understand the estimator proposed by [Lavenant et 
 al. 2020] which searches for the diffusion process that fits the observati
 ons with minimal entropy relative to a Wiener process. This estimator come
 s with consistency guarantees—for a suitable class of ground truth proce
 sses—and lends itself to computational methods with global optimality gu
 arantees. Its analysis is the occasion to review important tools from entr
 opic optimal transport — aka the Schrödinger bridge problem.\n 
LOCATION:Bernoulli Center
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR