BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//UM//UM*Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Detroit
TZURL:http://tzurl.org/zoneinfo/America/Detroit
X-LIC-LOCATION:America/Detroit
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20070311T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20071104T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240830T112455
DTSTART;TZID=America/Detroit:20241211T090000
DTEND;TZID=America/Detroit:20241211T200000
SUMMARY:Exhibition:Mrs. Dalloway and WWI: Home Front and War Front
DESCRIPTION:This exhibit explores the characters of Mrs. Dalloway through the lens of WWI and its aftershocks. It looks at those who fought in the trenches and those who watched from afar.\n\n[The exhibit includes references to suicide and Post Traumatic Stress Disorder\, which might be distressing for some visitors. Viewer discretion is advised.]\n\nWhile all of the action in Virginia Woolf’s modernist masterpiece takes place on a single day\, as preparations are made for Clarissa Dalloway’s evening party\, Woolf’s stream of consciousness writing takes us in the characters’ minds all the way from English drawing rooms to colonial India to the trenches of World War I.\n\nCheck today's Hatcher Gallery Exhibit Room hours: https://myumi.ch/PkQ2x
UID:123760-21851856@events.umich.edu
URL:https://events.umich.edu/event/123760
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Free,Library,Literature,Writing
LOCATION:Hatcher Graduate Library - Hatcher Gallery Exhibit Room, 1st Floor
CONTACT:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20241118T170624
DTSTART;TZID=America/Detroit:20241211T090000
DTEND;TZID=America/Detroit:20241211T100000
SUMMARY:Workshop / Seminar:Multilevel Approximation Schemes for Value-at-Risk and Expected Shortfall
DESCRIPTION:Evaluating the risk associated to a portfolio is important to\nregulators\, market exchanges and investors. The value-at-risk (VaR)\nand expected shortfall (ES) remain the most widely used risk measures\nin finance. Given a portfolio of future random loss X and a confidence\nlevel c in (0\,1)\, the VaR represents the quantile of X at level c (P(X\nVaR) = 1-c) and the ES the average loss given that X exceeds the\nVaR\, i.e. the superquantile of X at level c (ES = E[X|X > VaR]).\n\nComputing efficiently the VaR and ES of a given portfolio constitutes\nan active field of research. Rockafeller and Uryasev (2000) show that\,\nunder suitable assumptions\, the VaR and ES can be jointly retrieved as\nsolutions to a stochastic convex program\, thus allowing to resort to\nstochastic approximation methods. In a realistic scenario\, the loss of\nthe portfolio is expressed in a nested way\, i.e. X = E[f(Y\, Z)|Y]\,\nwhere Y describes the risk factors influencing the portfolio up to\nsome time horizon T > 0\, Z the risk factors influencing it beyond T\,\nand f(Y\, Z) the subsequent cash flows. The conditioning is done with\nrespect to the information available at time T. When X cannot be\nsimulated exactly\, a natural solution consists in swapping X with a\nnested Monte Carlo estimate thereof within the stochastic\napproximation scheme for the VaR and ES. This solution nevertheless\nincreases the estimation complexity.\n\nWe endeavor to accelerate the stochastic approximation of the VaR and\nES in the nested loss case. The goalpost is to attain a quadratic\ncomplexity as is achieved by unbiased stochastic approximation in the\ncase where X can be simulated exactly.\nWe first present a nested stochastic approximation scheme\, which\nsimulates X with a bias\, and attains a complexity in O(n^3) to achieve\nan error in O(1/n). We then leverage the multilevel paradigm to bring\nthe estimation cost down to O(n^2.5) for the VaR and to O(n^2 ln(n)^2)\nfor the ES. Since these complexities can only be reached under\nadditional inaccessible conditions\, we develop an ergodic\nPolyak-Ruppert version of the multilevel algorithm and demonstrate its\nincreased numerical stability through appropriate central limit\ntheorems. Eventually\, to bridge the performance gap between the\nmultilevel and unbiased VaR schemes (in O(n^2.5) and O(n^2))\, we\nadaptively refine the Monte Carlo innovations digested by the\nmultilevel algorithm\, resulting in a complexity of O(n^2 ln(n)^2.5).\nAll the above results are exemplified through suitable numerical\nstudies that include realistic financial scenarios.
UID:129250-21862376@events.umich.edu
URL:https://events.umich.edu/event/129250
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:
LOCATION:Off Campus Location
CONTACT:
END:VEVENT
END:VCALENDAR