BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260829T082819EDT-2810Z95NaE@132.216.98.100
DTSTAMP:20260829T122819Z
DESCRIPTION:Title: Off-the-grid sparse estimation\n\n\n	Abstract: The behavi
 our of sparse regularization using the Lasso method is well understood whe
 n dealing with discretized linear models. However\, the behaviour of Lasso
  is poor when dealing with models with very large parameter spaces and in 
 recent years\, there has been much interest in the use of 'off-the-grid' a
 pproaches\, using a continuous parameter space in conjunction with convex 
 optimization problem over measures. In my talk\, I will present some recen
 t results which explain the behaviour of this method in arbitrary dimensio
 ns. Some highlights include the use of the Fisher metric to study the perf
 ormance of Blasso over general domains and the application of this for qua
 ntitative MRI.\n\nFor Zoom meeting information please contact Tim.Hoheisel
  [at] mcgill.ca\n
DTSTART:20210315T131500Z
DTEND:20210315T131500Z
SUMMARY:Clarice Poon (University of Bath)
URL:https://www.mcgill.ca/mathstat/channels/event/clarice-poon-university-b
 ath-329614
END:VEVENT
END:VCALENDAR