BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20190719T085744Z
LOCATION:HG EO Nord
DTSTART;TZID=Europe/Stockholm:20190613T195000
DTEND;TZID=Europe/Stockholm:20190613T215000
UID:submissions.pasc-conference.org_PASC19_sess179_post127@linklings.com
SUMMARY:EAD01 - Deep Equilibrium Nets
DESCRIPTION:Poster\n\n\nEAD01 - Deep Equilibrium Nets\n\nAzinovic, Gaegauf
 , Scheidegger\n\nWe propose a grid-free, global solution method to compute
  approximate recursive equilibria for stochastic economies with a high-dim
 ensional state space in discrete time. We use deep neural nets to approxim
 ate the equilibrium demand functions. The key innovation of our paper is t
 o use the implied error in the optimality conditions as loss function. Con
 sequently, training data can be generated at virtually zero cost, since ne
 ither sets of nonlinear equations nor optimization problems need to be sol
 ved. To illustrate the applicability of the proposed method, we solve for 
 an approximate equilibrium in an overlapping generations model with 60 gen
 erations, aggregate uncertainty, and occasionally binding constraints. In 
 our numerical experiments on a Cray XC50 "Piz Daint" system at the Swiss N
 ational Supercomputer Centre (CSCS), we obtain average relative errors in 
 the Euler equations of the order ~ 10^(-3) when applying a densely connect
 ed deep neural net with two hidden layers.
END:VEVENT
END:VCALENDAR