BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Causal Representation Learning - Chaochao Lu\, University of Cambr
 idge
DTSTART:20210310T110000Z
DTEND:20210310T123000Z
UID:TALK157303@talks.cam.ac.uk
CONTACT:Elre Oldewage
DESCRIPTION:In recent years\, there is growing interest in integrating mac
 hine learning with causality\, as both communities are realising that one 
 can benefit from the advances of the other. In this talk\, we first review
  fundamental concepts of causal inference in relation to key problems of m
 achine learning to show how causality can contribute to machine learning. 
 Then\, since most work in causality is predicated on that causal variables
  are given\, we discuss how to discover high-level causal variables from l
 ow-level observations by leveraging machine learning methods\, which is a 
 central problem for causality and AI. Finally\, we showcase a series of re
 cent work on designing practical algorithms to address this problem.\n\nRe
 ferences:\n[1] Schölkopf et al. Towards Causal Representation Learning. 2
 021\n[2] Peters et al. Causal Inference using Invariant Prediction: Identi
 fication and Confidence Intervals. 2015\n[3] Arjovsky et al. Invariant Ris
 k Minimization. 2019\n[4] Lu et al. Nonlinear Invariant Risk Minimization:
  A Causal Approach. 2021
LOCATION:https://eng-cam.zoom.us/j/86068703738?pwd=YnFleXFQOE1qR1h6Vmtwbno
 0LzFHdz09
END:VEVENT
END:VCALENDAR