Statistics Colloquium : Dr. Yaakov Malinovsky

UMBC

Location

Mathematics/Psychology : 101

Date & Time

September 6, 2019, 11:00 am12:00 pm

Description

Title: 
A Unified Approach for Solving Sequential Selection Problems.

Abstract:
In this work we develop a unified approach for solving a wide class of sequential selection problems. This class includes, but is not limited to, selection problems with no-information, rank-dependent rewards, and considers both  fixed as well as random problem horizons. The proposed framework is based on a reduction of the original selection problem to one of optimal stopping for a sequence of judiciously constructed independent random variables. We demonstrate that our approach allows exact and efficient computation  of optimal policies and various performance metrics thereof for a variety of sequential selection problems, several of which have not been solved to date.

Acknowledgement:
This is joint work with Alexander Goldenshluger from University of Haifa, Israel, and Assaf Zeevi from Columbia University, USA.