A parallel method for large scale convex regression problems

Research output: Contribution to journalConference article

3 Citations (Scopus)

Abstract

Convex regression (CR) problem deals with fitting a convex function to a finite number of observations. It has many applications in various disciplines, such as statistics, economics, operations research, and electrical engineering. Computing the least squares (LS) estimator via solving a quadratic program (QP) is the most common technique to fit a piecewise-linear convex function to the observed data. Since the number of constraints in the QP formulation increases quadratically in N, the number of observed data points, computing the LS estimator is not practical using interior point methods when N is very large. The first-order method proposed in this paper carefully manages the memory usage through parallelization, and efficiently solves large-scale instances of CR.

Original languageEnglish (US)
Article number7040283
Pages (from-to)5710-5717
Number of pages8
JournalProceedings of the IEEE Conference on Decision and Control
Volume2015-February
Issue numberFebruary
DOIs
StatePublished - Jan 1 2014
Event2014 53rd IEEE Annual Conference on Decision and Control, CDC 2014 - Los Angeles, United States
Duration: Dec 15 2014Dec 17 2014

Fingerprint

Parallel Methods
Quadratic Program
Regression
Least Squares Estimator
Operations research
Convex function
Electrical engineering
Electrical Engineering
Computing
Interior Point Method
Statistics
Operations Research
Data storage equipment
Piecewise Linear
Parallelization
Linear Function
Economics
First-order
Formulation

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Modeling and Simulation
  • Control and Optimization

Cite this

@article{a8803bead8d143f3bb103249a7585c86,
title = "A parallel method for large scale convex regression problems",
abstract = "Convex regression (CR) problem deals with fitting a convex function to a finite number of observations. It has many applications in various disciplines, such as statistics, economics, operations research, and electrical engineering. Computing the least squares (LS) estimator via solving a quadratic program (QP) is the most common technique to fit a piecewise-linear convex function to the observed data. Since the number of constraints in the QP formulation increases quadratically in N, the number of observed data points, computing the LS estimator is not practical using interior point methods when N is very large. The first-order method proposed in this paper carefully manages the memory usage through parallelization, and efficiently solves large-scale instances of CR.",
author = "Aybat, {Necdet S.} and Zi Wang",
year = "2014",
month = "1",
day = "1",
doi = "10.1109/CDC.2014.7040283",
language = "English (US)",
volume = "2015-February",
pages = "5710--5717",
journal = "Proceedings of the IEEE Conference on Decision and Control",
issn = "0191-2216",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "February",

}

A parallel method for large scale convex regression problems. / Aybat, Necdet S.; Wang, Zi.

In: Proceedings of the IEEE Conference on Decision and Control, Vol. 2015-February, No. February, 7040283, 01.01.2014, p. 5710-5717.

Research output: Contribution to journalConference article

TY - JOUR

T1 - A parallel method for large scale convex regression problems

AU - Aybat, Necdet S.

AU - Wang, Zi

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Convex regression (CR) problem deals with fitting a convex function to a finite number of observations. It has many applications in various disciplines, such as statistics, economics, operations research, and electrical engineering. Computing the least squares (LS) estimator via solving a quadratic program (QP) is the most common technique to fit a piecewise-linear convex function to the observed data. Since the number of constraints in the QP formulation increases quadratically in N, the number of observed data points, computing the LS estimator is not practical using interior point methods when N is very large. The first-order method proposed in this paper carefully manages the memory usage through parallelization, and efficiently solves large-scale instances of CR.

AB - Convex regression (CR) problem deals with fitting a convex function to a finite number of observations. It has many applications in various disciplines, such as statistics, economics, operations research, and electrical engineering. Computing the least squares (LS) estimator via solving a quadratic program (QP) is the most common technique to fit a piecewise-linear convex function to the observed data. Since the number of constraints in the QP formulation increases quadratically in N, the number of observed data points, computing the LS estimator is not practical using interior point methods when N is very large. The first-order method proposed in this paper carefully manages the memory usage through parallelization, and efficiently solves large-scale instances of CR.

UR - http://www.scopus.com/inward/record.url?scp=84971200584&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84971200584&partnerID=8YFLogxK

U2 - 10.1109/CDC.2014.7040283

DO - 10.1109/CDC.2014.7040283

M3 - Conference article

AN - SCOPUS:84971200584

VL - 2015-February

SP - 5710

EP - 5717

JO - Proceedings of the IEEE Conference on Decision and Control

JF - Proceedings of the IEEE Conference on Decision and Control

SN - 0191-2216

IS - February

M1 - 7040283

ER -