BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:2300@i2m.univ-amu.fr
DTSTART;TZID=Europe/Paris:20180413T140000
DTEND;TZID=Europe/Paris:20180413T150000
DTSTAMP:20180329T120000Z
URL:https://www.i2m.univ-amu.fr/evenements/stochastic-subsampling-for-fact
 orizing-huge-matrices/
SUMMARY: (...): Stochastic subsampling for factorizing huge matrices
DESCRIPTION:: We present a matrix-factorization algorithm that scales to in
 put matrices with both huge number of rows and columns. Learned factors ma
 y be sparse or dense and/or non-negative\, which makes our algorithm suita
 ble for dictionary learning\, sparse component analysis\, and non-negative
  matrix factorization. Our algorithm streams matrix columns while subsampl
 ing them to iteratively learn the matrix factors. At each iteration\, the 
 row dimension of a new sample is reduced by subsampling\, resulting in low
 er time complexity compared to a simple streaming algorithm. Our method co
 mes with convergence guarantees to reach a stationary point of the matrix-
 factorization problem. We demonstrate its efficiency on massive functional
  Magnetic Resonance Imaging data (2 TB)\, and on patches extracted from hy
 perspectral images (103 GB). For both problems\, which involve different p
 enalties on rows and columns\, we obtain      significant speed-ups compar
 ed to state-of-the-art algorithms.http://team.inria.fr/parietal/team-membe
 rs/arthur-mensch/
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:DAYLIGHT
DTSTART:20180325T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR