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:20180305T010151Z
DTSTART;TZID=America/Los_Angeles:20180309T140000
DTEND;TZID=America/Los_Angeles:20180309T150000
TRANSP:OPAQUE
SUMMARY:BLISS Seminar: Nonconvex Sparse Deconvolution: Geometry and Efficient Methods
UID:116115-ucb-events-calendar@berkeley.edu
ORGANIZER;CN="UC Berkeley Calendar Network":
LOCATION:540 Cory Hall
DESCRIPTION:John Wright\, Associate Professor\, Columbia University\n\nThe problem of decomposing a given dataset as a superposition of basic motifs arises in a wide range of application areas\, including neural spike sorting and the analysis of astrophysical and microscopy data. Motivated by these problems\, we study a ``short-and-sparse’’ deconvolution problem\, in which the goal is to recover a short motif a from its convolution with a random spike train x. We formulate this problem as optimization over the sphere. We analyze the geometry of this (nonconvex) optimization problem\, and argue that when the target spike train is sufficiently sparse\, then on a region of the sphere\, every local minimum is equivalent to the ground truth\, up to symmetry (here a signed shift). This characterization obtains\, e.g.\, for generic kernels of length k\, when the sparsity rate of the spike train is proportional to k^{-2/3} (i.e.\, roughly k^{1/3} spikes in each length-k window). This geometric characterization implies that efficient methods obtain the ground truth under the same conditions. \n\nOur analysis highlights the key roles of symmetry and negative curvature in the behavior of efficient methods. We sketch connections to broader families of “benign” nonconvex problems in data representation and imaging\, in which efficient methods obtain global optima independent of initialization. We describe experiments in computer vision and scanning tunneling microscopy\, where nonconvex optimization supports new data analysis and data acquisition strategies.\n\nJoint work with Yuqian Zhang\, Yenson Lau\, Han-Wen Kuo\, Dar Gilboa\, Sky Cheung\, Abhay Pasupathy.
URL:http://events.berkeley.edu/index.php/calendar/sn/pubaff.html?event_ID=116115&view=preview
SEQUENCE:0
CLASS:PUBLIC
CREATED:20180305T010151Z
LAST-MODIFIED:20180305T163707Z
X-MICROSOFT-CDO-BUSYSTATUS:BUSY
X-MICROSOFT-CDO-INSTTYPE:0
X-MICROSOFT-CDO-IMPORTANCE:1
X-MICROSOFT-CDO-OWNERAPPTID:-1
END:VEVENT
END:VCALENDAR