BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20250918T054322EDT-2845ihpmI4@132.216.98.100
DTSTAMP:20250918T094322Z
DESCRIPTION:Title: Incorporating data into the maximum entropy to the mean 
 framework for Image processing\n\nAbstract: Ill-posed linear inverse probl
 ems are of fundamental interest in a wide array of mathematical\, physical
 \, and machine learning applications. For many image recovery applications
  one can enforce solution regularity via prior\, problem specific\, knowle
 dge. One such method is via the principle of maximum entropy to the mean\,
  which solves a high-level distribution valued problem to denoise and debl
 ur images. This framework has seen recent success in the realm of blind ba
 rcode deblurring and other structured image classes.\n\nWhile the current 
 literature of maximum entropy has both rich theoretical justification and 
 recovery guarantees\, there has not yet been any work to incorporate data-
 driven priors into this regime\, in the flavor of classical machine learni
 ng approaches. By constructing priors from data\, one can boost the perfor
 mance of this method\, while maintaining error bounds. This is a key requi
 rement for applications in fields such as medical imaging\, where failure 
 cases must be well understood.\n\nReferences: \n\n\n	The maximum entropy on
  the mean for image deblurring. Rioux\, Choksi\, Hoheisel et. al. ( https:
 //arxiv.org/abs/2002.10434 )\n	Maximum entropy on the mean and the Cramer r
 ate function in statistical estimation and inverse problems. Vaisbord et e
 l. ( https://arxiv.org/abs/2211.05205 )\n\n\n \n
DTSTART:20231101T170000Z
DTEND:20231101T180000Z
LOCATION:Room 1214\, Burnside Hall\, CA\, QC\, Montreal\, H3A 0B9\, 805 rue
  Sherbrooke Ouest
SUMMARY:Matthew King-Roskamp (9IÖÆ×÷³§Ãâ·Ñ)
URL:/mathstat/channels/event/matthew-king-roskamp-mcgi
 ll-university-352359
END:VEVENT
END:VCALENDAR