BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//University of California\, Berkeley//UCB Events Calendar//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
DTSTART:19701029T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:19700402T020000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20190225T081010Z
DTSTART;TZID=America/Los_Angeles:20190226T150000
DTEND;TZID=America/Los_Angeles:20190226T170000
TRANSP:OPAQUE
SUMMARY:Sparse Generalized Eigenvalue Problem and its Application in Neuroscience
UID:124181-ucb-events-calendar@berkeley.edu
ORGANIZER;CN="UC Berkeley Calendar Network":
LOCATION:5101 Berkeley Way West
DESCRIPTION:Kean Ming Tan\, PhD\, School of Statistics\, University of Minnesota\n\nSparse generalized eigenvalue problem (GEP) plays a pivotal role in a large family of high-dimensional learning tasks\, including sparse Fisherâ€™s discriminant analysis\, canonical correlation analysis\, and sufficient dimension reduction. Most of the existing methods and theory in the context of specific statistical models that can be recast into sparse GEP require restrictive structural assumptions on the input matrices. This talk will focus on a two-stage computational framework for solving the sparse GEP. At the first stage\, we solve a convex relaxation of the sparse GEP. Taking the solution as an initial value\, we then exploit a non-convex optimization perspective and propose the truncated Rayleigh flow method (Rifle) to estimate the leading generalized eigenvector\, and show that it converges linearly to a solution with the optimal statistical rate of convergence. Theoretically\, our method significantly improves upon the existing literature by eliminating the structural assumptions on the input matrices. Numerical studies in the context of several statistical models are provided to validate the theoretical results. We then apply the proposed method on an electrocorticography dataset to understand how human brains recall sequences of words.
URL:http://events.berkeley.edu/index.php/calendar/sn/pubaff.html?event_ID=124181&view=preview
SEQUENCE:0
CLASS:PUBLIC
CREATED:20190225T081010Z
LAST-MODIFIED:20190225T081010Z
X-MICROSOFT-CDO-BUSYSTATUS:BUSY
X-MICROSOFT-CDO-INSTTYPE:0
X-MICROSOFT-CDO-IMPORTANCE:1
X-MICROSOFT-CDO-OWNERAPPTID:-1
END:VEVENT
END:VCALENDAR