BEGIN:VCALENDAR
PRODID:-//Columba Systems Ltd//NONSGML CPNG/SpringViewer/ICal Output/3.3-
 M3//EN
VERSION:2.0
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
DTSTAMP:20260622T173306Z
DTSTART:20260623T100000Z
DTEND:20260623T110000Z
SUMMARY:SQUIDS Seminar: Bayesian inference for rough feature reconstructi
 ons
UID:{http://www.columbasystems.com/customers/uom/gpp/eventid/}b2c5-mqphul
 ca-z6bjbi
DESCRIPTION:Speaker: Lassi Roininen (LUT University in Finland\; currentl
 y a Visiting Fellow at Clare Hall\, Cambridge)\n\nAbstract: Edges in ima
 ging\, that is sharp discontinuities in intensity\, pose a significant c
 hallenge for inverse problems algorithms that often rely on Gaussian ass
 umptions. Non-Gaussian heavy-tailed priors\, which can better model the 
 sparsity and sharp transitions inherent in edges\, offer an alternative 
 for edge-preserving image reconstructions. We consider the inherent diff
 iculties in handling edges and highlight the potential of heavy-tailed p
 rior models to transform this problem into a practical engineering solut
 ion.
STATUS:TENTATIVE
TRANSP:TRANSPARENT
CLASS:PUBLIC
LOCATION:G.108\, Alan Turing Building\, Manchester
END:VEVENT
END:VCALENDAR