BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://caida.ubc.ca//NONSGML iCalcreator 2.41.92//
CALSCALE:GREGORIAN
METHOD:PUBLISH
UID:34313366-6137-4930-b830-333363346163
X-WR-RELCALID:efc09d74-9c93-479e-a94f-485231ddccde
X-WR-TIMEZONE:America/Vancouver
X-WR-CALNAME:Neural Stochastic Differential Equations for Irregularly-Sampl
 ed Time Series - David Duvenaud\, Assistant Professor\, U of T
BEGIN:VTIMEZONE
TZID:America/Vancouver
TZUNTIL:20211107T090000Z
BEGIN:STANDARD
TZNAME:PST
DTSTART:20191103T020000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RDATE:20201101T020000
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:PDT
DTSTART:20190310T020000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RDATE:20200308T020000
RDATE:20210314T020000
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:158111e0-c68f-415c-8aa5-735d48f2a42d
DTSTAMP:20260501T043505Z
CLASS:PUBLIC
CREATED:20191119T231931Z
DESCRIPTION:Abstract: Much real-world data is sampled at irregular interval
 s\, but most time series models require regularly-sampled data. Continuous
 -time state-space models can handle address this problem\, but until now o
 nly linear-Gaussian or deterministic models were efficiently trainable. We
  construct scalable algorithm for computing gradients of samples from stoc
 hastic differential equations\, and for gradient-based stochastic variatio
 nal inference in function space\, all with the use of adaptive black-box S
 DE solvers. This allows us to fit a new family of richly-parameterized dis
 tributions over…
DTSTART;TZID=America/Vancouver:20191206T113000
DTEND;TZID=America/Vancouver:20191206T123000
LAST-MODIFIED:20210611T171232Z
LOCATION:Hugh Dempster Pavilion (DMP) - 110\, 6245 Agronomy Road\, Vancouve
 r\, BC
SUMMARY:Neural Stochastic Differential Equations for Irregularly-Sampled Ti
 me Series - David Duvenaud\, Assistant Professor\, U of T
TRANSP:OPAQUE
URL:https://caida.ubc.ca/event/neural-stochastic-differential-equations-irr
 egularly-sampled-time-series-david-duvenaud
END:VEVENT
END:VCALENDAR