BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//University of Utah Math Department//Importance sampling in large-scale machine learning problems: why it works and how it can help//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Importance sampling in large-scale machine learning problems: why it works and how it can help
X-WR-CALDESC:Importance sampling in large-scale machine learning problems: why it works and how it can help at University of Utah Mathematics Department
X-WR-TIMEZONE:America/Denver
BEGIN:VEVENT
UID:20151105T160000-rachel-ward@math.utah.edu
DTSTART;TZID=America/Denver:20151105T160000
DTEND;TZID=America/Denver:20151105T170000
DTSTAMP:20260922T150858Z
SUMMARY:Importance sampling in large-scale machine learning problems: why it works and how it can help
DESCRIPTION:Speaker: Rachel Ward\, University of Texas at Austin\n\nA recent trend in signal processing and machine learning research is that exact reconstruction is achievable from highly subsampled data by passing to nonlinear, sparsity-inducing, reconstruction methods such as l1 minimization. Such guarantees often require strong structural conditions on the data …

LOCATION:LCB 219

URL:https://www.math.utah.edu/research/colloquia/2015-11-05-rachel-ward/
END:VEVENT
END:VCALENDAR