BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260125T031136EST-3641DaFBOo@132.216.98.100
DTSTAMP:20260125T081136Z
DESCRIPTION:Title: On LASSO parameter sensitivity.\n\nABSTRACT :\n	Compresse
 d sensing theory explains why LASSO programs recover structured high-dimen
 sional signals with minimax order-optimal error. Yet\, the optimal choice 
 of the program's governing parameter is often unknown in practice. It is s
 till unclear how variation of the governing parameter impacts recovery err
 or in compressed sensing\, which is otherwise provably stable and robust. 
 We provide an overview of parameter sensitivity in LASSO programs in the s
 etting of proximal denoising\; and of compressed sensing with subgaussian 
 measurement matrices and gaussian noise. We demonstrate how two popular el
 l-1 minimization programs exhibit sensitivity with respect to their parame
 ter choice and illustrate the theory with numerical simulations. For examp
 le\, a 1% error in the estimate of a parameter can cause the error to incr
 ease by a factor of 10^9\, while choosing a different LASSO program avoids
  such sensitivity issues. We hope that revealing parameter sensitivity reg
 imes of LASSO programs helps to inform a practitioner's choice.\n\nZoom Me
 eting :\n\nhttps://us06web.zoom.us/j/85327310903?pwd=SlhEak53S2xrNkVYKzl4Y
 Ud5KzBudz09\n\nMeeting ID: 853 2731 0903\n	Password: 383854\n
DTSTART:20211025T200000Z
DTEND:20211025T210000Z
LOCATION:Room 1104\, Burnside Hall\, CA\, QC\, Montreal\, H3A 0B9\, 805 rue
  Sherbrooke Ouest
SUMMARY:Aaron Berk (UBC)
URL:/mathstat/channels/event/aaron-berk-ubc-334359
END:VEVENT
END:VCALENDAR