BEGIN:VCALENDAR VERSION:2.0 PRODID:researchseminars.org CALSCALE:GREGORIAN X-WR-CALNAME:researchseminars.org BEGIN:VEVENT SUMMARY:Amir Beck (Tel-Aviv University) DTSTART:20200907T133000Z DTEND:20200907T143000Z DTSTAMP:20260423T021005Z UID:OWOS/16 DESCRIPTION:Title: Du al Randomized Coordinate Descent Method for Solving a Class of Nonconvex P roblems\nby Amir Beck (Tel-Aviv University) as part of One World Optim ization seminar\n\n\nAbstract\nWe consider a nonconvex optimization proble m consisting of maximizing the difference of two convex functions. We pres ent a randomized method that requires low computational effort at each ite ration. The described method is a randomized coordinate descent method emp loyed on the so-called Toland-dual problem. We prove subsequence convergen ce to dual stationarity points\, a new notion that we introduce and shown to be tighter than the standard criticality. Almost sure rate of convergen ce of an optimality measure of the dual sequence is proven. We demonstrat e the potential of our results on three Principal Component Analysis (PCA) models resulting in extremely simple algorithms\nJoint work Marc Teboulle \n\nthe address and password of the zoom room of the seminar are sent by e -mail on the mailinglist of the seminar one day before each talk\n LOCATION:https://researchseminars.org/talk/OWOS/16/ END:VEVENT END:VCALENDAR