BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:On the Interplay of Optimal Transport and Distributionally Robust 
 Optimization
DTSTART:20230331T110000
DTEND:20230331T120000
DTSTAMP:20261004T210026Z
UID:6e15a0bc387cf7cb315ed80413804f8f177d85960eacd03f2f248e82
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Daniel Kuhn EPFL\, Switzerland\nTitle: On the Interplay 
 of Optimal Transport and Distributionally Robust Optimization\n\nAbstract:
  Optimal Transport (OT) seeks the most efficient way to morph one probabil
 ity distribution into another one\, and Distributionally Robust Optimizati
 on (DRO) studies worst-case risk minimization problems under distributiona
 l ambiguity. It is well known that OT gives rise to a rich class of data-d
 riven DRO models\, where the decision-maker plays a zero-sum game against 
 nature who can adversely reshape the empirical distribution of the uncerta
 in problem parameters within a prescribed transportation budget. Even thou
 gh generic OT problems are computationally hard\, the Nash strategies of t
 he decision-maker and nature in OT-based DRO problems can often be compute
 d efficiently. In this talk we will uncover deep connections between robus
 tification and regularization\, and we will disclose striking properties o
 f nature’s Nash strategy\, which implicitly constructs an adversarial tr
 aining dataset. We will also show that OT-based DRO offers a principled ap
 proach to deal with distribution shifts and heterogeneous data sources\, a
 nd we will highlight new applications of OT-based DRO in machine learning\
 , statistics\, risk management and control. Finally\, we will argue that\,
  while OT is useful for DRO\, ideas from DRO can also help us to solve cha
 llenging OT problems.\n\nShort Biography: Daniel Kuhn holds the Chair of R
 isk Analytics and Optimization at EPFL. Before joining EPFL\, he was a fac
 ulty member at Imperial College London (2007-2013) and a postdoctoral rese
 archer at Stanford University (2005-2006). He received a PhD in Economics 
 from the University of St. Gallen in 2004 and an MSc in Theoretical Physic
 s from ETH Zurich in 1999. His research interests revolve around optimizat
 ion under uncertainty.\n\n\n 
LOCATION:ME C2 405 https://plan.epfl.ch/?room==ME%20C2%20405
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR