BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20190719T085743Z
LOCATION:HG F 1
DTSTART;TZID=Europe/Stockholm:20190612T153000
DTEND;TZID=Europe/Stockholm:20190612T160000
UID:submissions.pasc-conference.org_PASC19_sess145_msa195@linklings.com
SUMMARY:Large-Scale Sparse Inverse Covariance Matrix Estimation and its Ap
 plications
DESCRIPTION:Minisymposium\nComputer Science and Applied Mathematics, Chemi
 stry and Materials, Physics, Engineering\n\nLarge-Scale Sparse Inverse Cov
 ariance Matrix Estimation and its Applications\n\nBollhöfer, Schenk, Eftek
 hari, Scheidegger\n\nThe estimation of large sparse inverse covariance mat
 rices is an ubiquitous statistical problem in many application areas such 
 as mathematical finance or geology or many others. Numerical approaches ty
 pically rely on the maximum likelihood estimation or its negative log-like
 lihood function. When the Gaussian mean random field is expected to be spa
 rse, regularization techniques which add a sparsity prior have become popu
 lar to address this issue. Recently a quadratic approximate inverse covari
 ance method (QUIC) [1] has been proposed. The hallmark of this method is i
 ts superlinear to quadratic convergence which makes this algorithm to be a
 mong the most competitive methods. In this talk we present a sparse versio
 n (SQUIC) [2] of this method and we will demonstrate that using advanced s
 parse matrix technology the sparse version of QUIC is easily able to deal 
 with problems of size one million within a few minutes on modern multicore
  computers.<br />[1] C.J. Hsieh, M.A. Sustik, I.S. Dhillon, and P.K. Ravik
 umar. Sparse inverse covariance matrix estimation using quadratic approxim
 ation, in Advances in Neural Information Processing Systems, J. Shawe-Tayl
 or et al., eds., vol. 24, Neural Information Processing Systems Foundation
 , 2011, pp. 2330-2338.<br />[2] M. Bollhöfer, A. Eftekhari, S. Scheid
 egger, and O. Schenk. Large-Scale Sparse Inverse Covariance Matrix Estimat
 ion. <em>SIAM J. Sci. Comput., 41(1), A380-A401, 2019.</em>
END:VEVENT
END:VCALENDAR