BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//juliacon-local-paris-2025//talk//KTGPQE
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:DAYLIGHT
DTSTART:20241003T000000
TZNAME:CEST
TZOFFSETFROM:+0200
TZOFFSETTO:+0200
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20241027T030000
RDATE:20251026T030000
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20250330T030000
RDATE:20260329T030000
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Leveraging Sparsity to Accelerate Automatic Differentiation - Guil
 laume Dalle\, Adrian Hill
DTSTART;TZID=Europe/Paris:20251003T113000
DTEND;TZID=Europe/Paris:20251003T120000
DTSTAMP:20260819T092109Z
UID:pretalx-juliacon-local-paris-2025-KTGPQE@pretalx.com
DESCRIPTION:Jacobians and Hessians play vital roles in scientific computin
 g and machine learning\, from optimization to probabilistic modeling. Whil
 e these matrices are often considered too computationally expensive to cal
 culate\, their inherent sparsity can be leveraged to dramatically accelera
 te Automatic Differentiation (AD). By building on top of DifferentiationIn
 terface.jl\, we are able to bring Automatic Sparse Differentiation to all 
 major Julia AD backends\, including ForwardDiff and Enzyme.
LOCATION:Robert Faure Amphitheater
URL:https://pretalx.com/juliacon-local-paris-2025/talk/KTGPQE/
END:VEVENT
END:VCALENDAR