BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260114T163653Z
LOCATION:Meeting Room C4.9+C4.10\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231213T152000
DTEND;TZID=Australia/Melbourne:20231213T153000
UID:siggraphasia_SIGGRAPH Asia 2023_sess168_papers_906@linklings.com
SUMMARY:Joint Sampling and Optimisation for Inverse Rendering
DESCRIPTION:Martin Balint, Karol Myszkowski, Hans-Peter Seidel, and Gurpri
 t Singh (Max Planck Institute for Informatics)\n\nWhen dealing with diffic
 ult inverse problems such as inverse rendering, using Monte Carlo estimate
 d gradients to optimise parameters can slow down convergence due to varian
 ce. Averaging many gradient samples in each iteration reduces this varianc
 e trivially. However, for problems that require thousands of optimisation 
 iterations, the computational cost of this approach rises quickly.\n\nWe d
 erive a theoretical framework for interleaving sampling and optimisation. 
 We update and reuse past samples with low-variance finite-difference estim
 ators that describe the change in the estimated gradients between each ite
 ration. By optimally combining proportional and finite-difference samples,
  we continuously reduce the variance of our novel gradient meta-estimators
  throughout the optimisation process. We investigate how our estimator int
 erlinks with Adam and derive a stable combination.\n\nWe implement our met
 hod for inverse path tracing and demonstrate how our estimator speeds up c
 onvergence on difficult optimisation tasks.\n\nRegistration Category: Full
  Access\n\nSession Chair: Soo-Mi Choi (Sejong University)\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_906&sess=sess168
END:VEVENT
END:VCALENDAR