BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//RLASKEY//CALENDEROUS//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
DTSTAMP:20260812T023311Z
LAST-MODIFIED:20191029T144704Z
DTSTART:20191105T203000Z
DTEND:20191105T213000Z
UID:event2222@bu.edu
URL:http://physics.bu.edu/internal/events/show/2222
SUMMARY:Physics\, machine learning\, and networks
DESCRIPTION:Featuring Cristopher Moore\, Santa Fe Institute and Microsoft R
	esearch\n\nPart of the Physics Department Colloquia Series.\n\nThere is a d
	eep analogy between Bayesian inference — where we try to fit a model to d
	ata\, which has a ground-truth structure partly hidden by noise — and sta
	tistical physics. Many concepts like energy landscapes\, free energy\, and 
	phase transitions can be usefully carried over from physics to machine lear
	ning and computer science. At the very least\, these techniques are a sourc
	e of conjectures that have stimulated new work in probability\, combinatori
	cs\, and theoretical computer science. At their best\, they offer strong in
	tuitions about the structure of inference problems and possible algorithms 
	for them.\n\nOne recent success of this interface is the discovery of a pha
	se transition in community detection in networks. Analogous transitions exi
	st in many other inference problems\, where our ability to find patterns in
	 data jumps suddenly as a function of how noisy they are. I will discuss wh
	y and how this detectability transition occurs\, review what is known rigor
	ously\, and present a number of open questions that cry out for proofs.
LOCATION:SCI 109\, 590 Commonwealth Avenue\, 02215
STATUS:CONFIRMED
CLASS:PUBLIC
END:VEVENT
END:VCALENDAR