BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:From Causal Inference to Autoencoders and Gene Regulation
DTSTART:20191115T140000
DTEND:20191115T150000
DTSTAMP:20260609T210825Z
UID:a74a0dc3521658f9d6591031dedf1dc35e420a4f85fa8cf9f433e15e
CATEGORIES:Conferences - Seminars
DESCRIPTION:Professor Caroline Uhler\n\nCaroline Uhler recently joined ETH
  Zürich as Full Professor of Machine Learning\, Statistics and Genomics. 
 Prior to joining ETH Zürich\, she was Associate Professor at MIT. SHe hol
 ds a PhD in statistics from UC Berkeley\, spent a semester in the “Big D
 ata” program at the Simons Institute at UC Berkeley\, held postdoctoral 
 positions at the IMA and at ETH Zurich\, was assistant professor for 3 ye
 ars at IST Austria. Her research focuses in particular on graphical models
 \, causal inference\, algebraic statistics and applications to genomics\, 
 for example on linking the spatial organization of the DNA with gene regul
 ation.\nAbstract\n\nRecent progress in genomics makes it possible to perfo
 rm perturbation experiments at a very large scale. This motivates the deve
 lopment of a causal inference framework that is based on observational and
  interventional data. We characterize the causal relationships that are id
 entifiable and present the first provably consistent algorithm for learnin
 g a causal network from such data. I will then couple gene expression with
  the 3D genome organization. In particular\, we will discuss approaches fo
 r integrating different data modalities such as sequencing or imaging via 
 autoencoders. We end by a theoretical analysis of autoencoders linking ove
 rparameterization to memorization. In particular\, we will show that over
 parameterized autoencoders trained using standard optimization methods imp
 lement associative memory and provide a mechanism for memorization and ret
 rieval of real-valued data.\n 
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR