Take Action

Home | Faculty & Research Overview | Research

Research Details

On the Efficiency Loss of State-Independent Importance Sampling in the Presence of Heavy-Tails, Operations Research Letters

Abstract

We consider importance sampling simulation for estimating rare event probabilities in the presence of heavy-tailed distributions that have polynomial-like tails. In particular, we prove the following negative result: there does not exist an asymptotically optimal state-independent change-of-measure for estimating the probability that a random walk (respectively, queue length for a single server queue) exceeds a "high" threshold before going below zero (respectively, becoming empty). Furthermore, we derive explicit bounds on the best asymptotic variance reduction achieved by importance sampling relative to naive simulation. We illustrate through a simple numerical example that a good" state-dependent change-of-measure may be developed based on an approximation of the zero-variance measure

Type

Article

Author(s)

Achal Bassamboo, Sandeep Juneja, Assaf Zeevi

Date Published

2007

Citations

Bassamboo, Achal, Sandeep Juneja, and Assaf Zeevi. 2007. On the Efficiency Loss of State-Independent Importance Sampling in the Presence of Heavy-Tails. Operations Research Letters. 35(2): 251-260.

KELLOGG INSIGHT

Explore leading research and ideas

Find articles, podcast episodes, and videos that spark ideas in lifelong learners, and inspire those looking to advance in their careers.
learn more

COURSE CATALOG

Review Courses & Schedules

Access information about specific courses and their schedules by viewing the interactive course scheduler tool.
LEARN MORE

DEGREE PROGRAMS

Discover the path to your goals

Whether you choose our Full-Time, Part-Time or Executive MBA program, you’ll enjoy the same unparalleled education, exceptional faculty and distinctive culture.
learn more

Take Action