BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Facultad de Economía y Negocios - ECPv5.14.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Facultad de Economía y Negocios
X-ORIGINAL-URL:https://fen.uahurtado.cl
X-WR-CALDESC:Eventos para Facultad de Economía y Negocios
BEGIN:VTIMEZONE
TZID:America/Santiago
BEGIN:STANDARD
TZOFFSETFROM:-0300
TZOFFSETTO:-0400
TZNAME:-04
DTSTART:20210404T030000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0400
TZOFFSETTO:-0300
TZNAME:-03
DTSTART:20210905T040000
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Santiago:20211129T150000
DTEND;TZID=America/Santiago:20211129T160000
DTSTAMP:20260416T080736
CREATED:20211125T160147Z
LAST-MODIFIED:20211125T160147Z
UID:23496-1638198000-1638201600@fen.uahurtado.cl
SUMMARY:Seminario académico UNAB-UAH 2021- Invitado: Emerson Melo\, profesor en Indiana University Bloomington
DESCRIPTION:La Facultad de Economía y Negocios de la Universidad Alberto Hurtado en conjunto con la Facultad de Economía y Negocios de la Universidad Andrés Bello\, tienen el agrado de invitarte a un nuevo Seminario Académico de Economía 2021. \nEn esta ocasión Emerson Melo\, assistant professor at the Department of Economics at Indiana University Bloomington\, presentará su trabajo «Learning in Random Utility Models via Online Decision Problems». \n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nAbstract: \nThis paper studies the Random Utility Model (RUM) in environments where the decision maker is imperfectly informed about the payoffs associated to each of the alternatives he faces. By embedding the RUM into an online decision problem\, we make four contributions. First\, we propose a gradient-based learning algorithm and show that a large class of RUMs are Hannan consistent (Hannan\, 1957); that is\, the average difference between the expected payoffs generated by a RUM and that of the best fixed policy in hindsight goes to zero as the number of periods increase. Second\, we show that the class of Generalized Extreme Value (GEV) models can be implemented with our learning algorithm. Examples in the GEV class include the Nested Logit\, Ordered\, and Product Differentiation models among many others. Third\, we show that our gradient-based algorithm is the dual\, in a convex analysis sense\, of the Follow the Regularized Leader (FTRL) algorithm\, which is widely used in the Machine Learning literature. Finally\, we discuss how our approach can incorporate recency bias and be used to implement prediction markets in general environments. \nCONÉCTATE AQUÍ
URL:https://fen.uahurtado.cl/calendario/seminario-academico-unab-uah-2021-invitado-emerson-melo-profesor-en-indiana-university-bloomington/
CATEGORIES:Eventos Economía
END:VEVENT
END:VCALENDAR