Prismatic algorithm for discrete D.C. programming problem

Yoshinobu Kawahara, Takashi Washio

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

In this paper, we propose the first exact algorithm for minimizing the difference of two submodular functions (D.S.), i.e., the discrete version of the D.C. programming problem. The developed algorithm is a branch-and-bound-based algorithm which responds to the structure of this problem through the relationship between submodularity and convexity. The D.S. programming problem covers a broad range of applications in machine learning. In fact, this generalizes any set-function optimization. We empirically investigate the performance of our algorithm, and illustrate the difference between exact and approximate solutions respectively obtained by the proposed and existing algorithms in feature selection and discriminative structure learning.

Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems 24
Subtitle of host publication25th Annual Conference on Neural Information Processing Systems 2011, NIPS 2011
Publication statusPublished - Dec 1 2011
Externally publishedYes
Event25th Annual Conference on Neural Information Processing Systems 2011, NIPS 2011 - Granada, Spain
Duration: Dec 12 2011Dec 14 2011

Publication series

NameAdvances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011, NIPS 2011

Conference

Conference25th Annual Conference on Neural Information Processing Systems 2011, NIPS 2011
CountrySpain
CityGranada
Period12/12/1112/14/11

Fingerprint

Learning systems
Feature extraction

All Science Journal Classification (ASJC) codes

  • Information Systems

Cite this

Kawahara, Y., & Washio, T. (2011). Prismatic algorithm for discrete D.C. programming problem. In Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011, NIPS 2011 (Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011, NIPS 2011).

Prismatic algorithm for discrete D.C. programming problem. / Kawahara, Yoshinobu; Washio, Takashi.

Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011, NIPS 2011. 2011. (Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011, NIPS 2011).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kawahara, Y & Washio, T 2011, Prismatic algorithm for discrete D.C. programming problem. in Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011, NIPS 2011. Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011, NIPS 2011, 25th Annual Conference on Neural Information Processing Systems 2011, NIPS 2011, Granada, Spain, 12/12/11.
Kawahara Y, Washio T. Prismatic algorithm for discrete D.C. programming problem. In Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011, NIPS 2011. 2011. (Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011, NIPS 2011).
Kawahara, Yoshinobu ; Washio, Takashi. / Prismatic algorithm for discrete D.C. programming problem. Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011, NIPS 2011. 2011. (Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011, NIPS 2011).
@inproceedings{43fd65c1a8424f3bb3a5ecf1c25656e8,
title = "Prismatic algorithm for discrete D.C. programming problem",
abstract = "In this paper, we propose the first exact algorithm for minimizing the difference of two submodular functions (D.S.), i.e., the discrete version of the D.C. programming problem. The developed algorithm is a branch-and-bound-based algorithm which responds to the structure of this problem through the relationship between submodularity and convexity. The D.S. programming problem covers a broad range of applications in machine learning. In fact, this generalizes any set-function optimization. We empirically investigate the performance of our algorithm, and illustrate the difference between exact and approximate solutions respectively obtained by the proposed and existing algorithms in feature selection and discriminative structure learning.",
author = "Yoshinobu Kawahara and Takashi Washio",
year = "2011",
month = "12",
day = "1",
language = "English",
isbn = "9781618395993",
series = "Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011, NIPS 2011",
booktitle = "Advances in Neural Information Processing Systems 24",

}

TY - GEN

T1 - Prismatic algorithm for discrete D.C. programming problem

AU - Kawahara, Yoshinobu

AU - Washio, Takashi

PY - 2011/12/1

Y1 - 2011/12/1

N2 - In this paper, we propose the first exact algorithm for minimizing the difference of two submodular functions (D.S.), i.e., the discrete version of the D.C. programming problem. The developed algorithm is a branch-and-bound-based algorithm which responds to the structure of this problem through the relationship between submodularity and convexity. The D.S. programming problem covers a broad range of applications in machine learning. In fact, this generalizes any set-function optimization. We empirically investigate the performance of our algorithm, and illustrate the difference between exact and approximate solutions respectively obtained by the proposed and existing algorithms in feature selection and discriminative structure learning.

AB - In this paper, we propose the first exact algorithm for minimizing the difference of two submodular functions (D.S.), i.e., the discrete version of the D.C. programming problem. The developed algorithm is a branch-and-bound-based algorithm which responds to the structure of this problem through the relationship between submodularity and convexity. The D.S. programming problem covers a broad range of applications in machine learning. In fact, this generalizes any set-function optimization. We empirically investigate the performance of our algorithm, and illustrate the difference between exact and approximate solutions respectively obtained by the proposed and existing algorithms in feature selection and discriminative structure learning.

UR - http://www.scopus.com/inward/record.url?scp=84860643948&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84860643948&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84860643948

SN - 9781618395993

T3 - Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011, NIPS 2011

BT - Advances in Neural Information Processing Systems 24

ER -