Structured convex optimization under submodular constraints

Kiyohito Nagano, Yoshinobu Kawahara

Research output: Contribution to conferencePaper

7 Citations (Scopus)

Abstract

A number of discrete and continuous optimization problems in machine learning are related to convex minimization problems under submodular constraints. In this paper, we deal with a submodular function with a directed graph structure, and we show that a wide range of convex optimization problems under submodular constraints can be solved much more efficiently than general submodular optimization methods by a reduction to a maximum flow problem. Furthermore, we give some applications, including sparse optimization methods, in which the proposed methods are effective. Additionally, we evaluate the performance of the proposed method through computational experiments.

Original languageEnglish
Pages459-468
Number of pages10
Publication statusPublished - Nov 28 2013
Externally publishedYes
Event29th Conference on Uncertainty in Artificial Intelligence, UAI 2013 - Bellevue, WA, United States
Duration: Jul 11 2013Jul 15 2013

Conference

Conference29th Conference on Uncertainty in Artificial Intelligence, UAI 2013
CountryUnited States
CityBellevue, WA
Period7/11/137/15/13

Fingerprint

Convex optimization
Directed graphs
Learning systems
Experiments

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cite this

Nagano, K., & Kawahara, Y. (2013). Structured convex optimization under submodular constraints. 459-468. Paper presented at 29th Conference on Uncertainty in Artificial Intelligence, UAI 2013, Bellevue, WA, United States.

Structured convex optimization under submodular constraints. / Nagano, Kiyohito; Kawahara, Yoshinobu.

2013. 459-468 Paper presented at 29th Conference on Uncertainty in Artificial Intelligence, UAI 2013, Bellevue, WA, United States.

Research output: Contribution to conferencePaper

Nagano, K & Kawahara, Y 2013, 'Structured convex optimization under submodular constraints', Paper presented at 29th Conference on Uncertainty in Artificial Intelligence, UAI 2013, Bellevue, WA, United States, 7/11/13 - 7/15/13 pp. 459-468.
Nagano K, Kawahara Y. Structured convex optimization under submodular constraints. 2013. Paper presented at 29th Conference on Uncertainty in Artificial Intelligence, UAI 2013, Bellevue, WA, United States.
Nagano, Kiyohito ; Kawahara, Yoshinobu. / Structured convex optimization under submodular constraints. Paper presented at 29th Conference on Uncertainty in Artificial Intelligence, UAI 2013, Bellevue, WA, United States.10 p.
@conference{17d37b404b294215ac38383d9df2c0e1,
title = "Structured convex optimization under submodular constraints",
abstract = "A number of discrete and continuous optimization problems in machine learning are related to convex minimization problems under submodular constraints. In this paper, we deal with a submodular function with a directed graph structure, and we show that a wide range of convex optimization problems under submodular constraints can be solved much more efficiently than general submodular optimization methods by a reduction to a maximum flow problem. Furthermore, we give some applications, including sparse optimization methods, in which the proposed methods are effective. Additionally, we evaluate the performance of the proposed method through computational experiments.",
author = "Kiyohito Nagano and Yoshinobu Kawahara",
year = "2013",
month = "11",
day = "28",
language = "English",
pages = "459--468",
note = "29th Conference on Uncertainty in Artificial Intelligence, UAI 2013 ; Conference date: 11-07-2013 Through 15-07-2013",

}

TY - CONF

T1 - Structured convex optimization under submodular constraints

AU - Nagano, Kiyohito

AU - Kawahara, Yoshinobu

PY - 2013/11/28

Y1 - 2013/11/28

N2 - A number of discrete and continuous optimization problems in machine learning are related to convex minimization problems under submodular constraints. In this paper, we deal with a submodular function with a directed graph structure, and we show that a wide range of convex optimization problems under submodular constraints can be solved much more efficiently than general submodular optimization methods by a reduction to a maximum flow problem. Furthermore, we give some applications, including sparse optimization methods, in which the proposed methods are effective. Additionally, we evaluate the performance of the proposed method through computational experiments.

AB - A number of discrete and continuous optimization problems in machine learning are related to convex minimization problems under submodular constraints. In this paper, we deal with a submodular function with a directed graph structure, and we show that a wide range of convex optimization problems under submodular constraints can be solved much more efficiently than general submodular optimization methods by a reduction to a maximum flow problem. Furthermore, we give some applications, including sparse optimization methods, in which the proposed methods are effective. Additionally, we evaluate the performance of the proposed method through computational experiments.

UR - http://www.scopus.com/inward/record.url?scp=84888147975&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84888147975&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:84888147975

SP - 459

EP - 468

ER -