BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//RLASKEY//CALENDEROUS//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
DTSTAMP:20261021T161830Z
LAST-MODIFIED:20170906T184708Z
DTSTART:20170811T150000Z
DTEND:20170811T170000Z
UID:event1782@bu.edu
URL:http://physics.bu.edu/internal/events/show/1782
SUMMARY:Out-of-equilibrium states and quantum annealing speed up in non-con
	vex optimization and learning problems
DESCRIPTION:Featuring Riccardo Zecchina\n\nPart of the Condensed Matter The
	ory Seminar Series.\n\nQuantum annealers aim at solving non-convex optimiza
	tion problems by exploiting cooperative tunneling effects to escape local m
	inima. A key challenge is to identify classes of non-convex optimization pr
	oblems for which this scheme can induce an exponential speed up  compared t
	o thermal annealing. We show that this happens for a wide class of optimiza
	tion problems which are also central to machine learning. Their energy land
	scape is exponentially dominated by local minima that trap classical therma
	l annealers\, while quantum annealing converges efficiently to rare dense r
	egions of optimal solutions.  For non convex problems\, these will not in g
	eneral correspond to configuration dominating the  Gibbs measure.
LOCATION:SCI 328\, 590 Commonwealth Avenue\, 02215
STATUS:CONFIRMED
CLASS:PUBLIC
END:VEVENT
END:VCALENDAR