Estimating arrival rate of nonhomogeneous Poisson processes with semidefinite programming

Farid Alizadeh, David Papp

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

We present a summary of methods based on semidefinite programming for estimating arrival rate of nonhomogeneous Poisson processes from a finite set of observed data. Both one-dimensional time dependent, and multi-dimensional time and location dependent rates are considered. The arrival rate is a nonnegative function of time (or time and location). We also assume that it is a smooth function with continuous derivatives of up to certain order k. We estimate the rate function by one or multi-dimensional splines, with the additional condition that the underlying rate function is nonnegative. This approach results in an optimization problem over nonnegative polynomials, which can be modeled and solved using semidefinite programming. We also describe a method which requires only linear constraints. Numerical results based on e-mail arrival and highway accidents are presented.

Original languageEnglish (US)
Pages (from-to)291-308
Number of pages18
JournalAnnals of Operations Research
Volume208
Issue number1
DOIs
StatePublished - Sep 1 2013

Fingerprint

Poisson process
Semidefinite programming
Optimization problem
Splines
Electronic mail
Accidents
Polynomials
Derivatives

All Science Journal Classification (ASJC) codes

  • Decision Sciences(all)
  • Management Science and Operations Research

Cite this

@article{bd6a553e46544037b691720aab94d981,
title = "Estimating arrival rate of nonhomogeneous Poisson processes with semidefinite programming",
abstract = "We present a summary of methods based on semidefinite programming for estimating arrival rate of nonhomogeneous Poisson processes from a finite set of observed data. Both one-dimensional time dependent, and multi-dimensional time and location dependent rates are considered. The arrival rate is a nonnegative function of time (or time and location). We also assume that it is a smooth function with continuous derivatives of up to certain order k. We estimate the rate function by one or multi-dimensional splines, with the additional condition that the underlying rate function is nonnegative. This approach results in an optimization problem over nonnegative polynomials, which can be modeled and solved using semidefinite programming. We also describe a method which requires only linear constraints. Numerical results based on e-mail arrival and highway accidents are presented.",
author = "Farid Alizadeh and David Papp",
year = "2013",
month = "9",
day = "1",
doi = "10.1007/s10479-011-1020-2",
language = "English (US)",
volume = "208",
pages = "291--308",
journal = "Annals of Operations Research",
issn = "0254-5330",
publisher = "Springer Netherlands",
number = "1",

}

Estimating arrival rate of nonhomogeneous Poisson processes with semidefinite programming. / Alizadeh, Farid; Papp, David.

In: Annals of Operations Research, Vol. 208, No. 1, 01.09.2013, p. 291-308.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Estimating arrival rate of nonhomogeneous Poisson processes with semidefinite programming

AU - Alizadeh, Farid

AU - Papp, David

PY - 2013/9/1

Y1 - 2013/9/1

N2 - We present a summary of methods based on semidefinite programming for estimating arrival rate of nonhomogeneous Poisson processes from a finite set of observed data. Both one-dimensional time dependent, and multi-dimensional time and location dependent rates are considered. The arrival rate is a nonnegative function of time (or time and location). We also assume that it is a smooth function with continuous derivatives of up to certain order k. We estimate the rate function by one or multi-dimensional splines, with the additional condition that the underlying rate function is nonnegative. This approach results in an optimization problem over nonnegative polynomials, which can be modeled and solved using semidefinite programming. We also describe a method which requires only linear constraints. Numerical results based on e-mail arrival and highway accidents are presented.

AB - We present a summary of methods based on semidefinite programming for estimating arrival rate of nonhomogeneous Poisson processes from a finite set of observed data. Both one-dimensional time dependent, and multi-dimensional time and location dependent rates are considered. The arrival rate is a nonnegative function of time (or time and location). We also assume that it is a smooth function with continuous derivatives of up to certain order k. We estimate the rate function by one or multi-dimensional splines, with the additional condition that the underlying rate function is nonnegative. This approach results in an optimization problem over nonnegative polynomials, which can be modeled and solved using semidefinite programming. We also describe a method which requires only linear constraints. Numerical results based on e-mail arrival and highway accidents are presented.

UR - http://www.scopus.com/inward/record.url?scp=84883050399&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883050399&partnerID=8YFLogxK

U2 - 10.1007/s10479-011-1020-2

DO - 10.1007/s10479-011-1020-2

M3 - Article

AN - SCOPUS:84883050399

VL - 208

SP - 291

EP - 308

JO - Annals of Operations Research

JF - Annals of Operations Research

SN - 0254-5330

IS - 1

ER -