BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20250623T022857EDT-6274KHU9sb@132.216.98.100
DTSTAMP:20250623T062857Z
DESCRIPTION:Title: Off-the-grid sparse estimation\n\nAbstract:\n	The behavio
 ur of sparse regularization using the Lasso method is well understood when
  dealing with discretized linear models. However\, the behaviour of Lasso 
 is poor when dealing with models with very large parameter spaces and in r
 ecent years\, there has been much interest in the use of 'off-the-grid' ap
 proaches\, using a continuous parameter space in conjunction with convex o
 ptimization problem over measures. In my talk\, I will present some recent
  results which explain the behaviour of this method in arbitrary dimension
 s. Some highlights include the use of the Fisher metric to study the perfo
 rmance of Blasso over general domains and the application of this for quan
 titative MRI.\n\nFor Zoom information please contact tim.hoheisel [at] mcg
 ill.ca\n
DTSTART:20210315T200000Z
DTEND:20210315T210000Z
SUMMARY:Clarice Poon (University of Bath)
URL:/mathstat/channels/event/clarice-poon-university-b
 ath-329618
END:VEVENT
END:VCALENDAR