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:20241120T082409Z
LOCATION:HG D 1.2
DTSTART;TZID=Europe/Stockholm:20240605T120000
DTEND;TZID=Europe/Stockholm:20240605T123000
UID:submissions.pasc-conference.org_PASC24_sess110_msa132@linklings.com
SUMMARY:Deep Learning Solutions to Master Equations for Continuous Time He
 terogeneous Agent Macroeconomic Models
DESCRIPTION:Minisymposium\n\nJonathan Payne and Zhouzhou Gu (Princeton Uni
 versity), Mathieu Laurière (New York University), and Sebastian Merkel (Un
 iversity of Exeter)\n\nWe propose new global solution algorithms for conti
 nuous time heterogeneous agent economies with aggregate shocks.We first ap
 proximate the state space so the master equation becomes a high, but finit
 e, dimensional partial differential equation. We then approximate the valu
 e function using neural networks and solve the master equation using deep 
 learning tools. The main advantage of this technique is that it allows us 
 to find global solutions to high dimensional, non-linear problems. We cons
 ider two broad approaches to reducing the dimensionality of the problem: d
 iscretizing the number of agents and projecting the distribution. We demon
 strate our algorithms by solving two canonical models in the macroeconomic
 s literature: the Aiyagari (1994) model and the Krusell and Smith (1998) m
 odel.\n\nDomain: Applied Social Sciences and Humanities, Computational Met
 hods and Applied Mathematics\n\nSession Chairs: Aleksandra Friedl (ifo Ins
 titut), Simon Scheidegger (University of Lausanne), and Yucheng Yang (Univ
 ersity of Zurich)
END:VEVENT
END:VCALENDAR