BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Decodable and Unlearnable Phases and Transitions [Confirmed]
DTSTART:20260311T170000Z
DTEND:20260311T183000Z
DTSTAMP:20260510T152200Z
UID:indico-event-2151@events.perimeterinstitute.ca
DESCRIPTION:Speakers: Timothy Hsieh (Perimeter Institute for Theoretical P
 hysics)\n\nPhysics has been driven by the discovery of novel phases of mat
 ter\, largely in materials.  Recently\, the advent of both quantum error
  correction and machine learning\, viewed as physical phenomena\, has comp
 elled us to revisit the notion of a phase itself.  I will show how decod
 able/undecodable regimes of codes constitute distinct phases in a precise 
 sense\, and they furnish machine unlearnable/learnable phases of data.  
 I will demonstrate how conditional mutual information (CMI) serves as an e
 ssential quantity in characterizing the corresponding phases and transitio
 ns and thus provides a new diagnostic for both error correction thresholds
  and machine learnability of quantum and classical systems\, including rea
 l-world data.  \n\nhttps://events.perimeterinstitute.ca/event/2151/
LOCATION:PI/2-292 - Time Room (Perimeter Institute for Theoretical Physics
 )
URL:https://events.perimeterinstitute.ca/event/2151/
END:VEVENT
END:VCALENDAR