A Fixed-Point Analysis of Regularized Dual Averaging under Static Scenarios

Masahiro Yukawa, Isao Yamada

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

Abstract

In this paper, we analyze the properties of a fixed point of a certain mapping that is implicitly used in each of the regularized dual averaging (RDA) and projection-based RDA (PDA) algorithms. It turns out that, if the loss function has a nonexpansive (1-Lipschltz) gradient such as in the case of a half squared-distance function, RDA converges to a minimizer of the penalized loss function under a restrictive condition. Meanwhile, the fixed point for PDA gives a minimizer of the 'unpenalized' loss function. Some simulation studies are also presented to support the theoretical findings.

Original languageEnglish
Title of host publication2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages207-211
Number of pages5
ISBN (Electronic)9789881476852
DOIs
Publication statusPublished - 2019 Mar 4
Event10th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Honolulu, United States
Duration: 2018 Nov 122018 Nov 15

Publication series

Name2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings

Conference

Conference10th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018
CountryUnited States
CityHonolulu
Period18/11/1218/11/15

Fingerprint

Personal digital assistants

ASJC Scopus subject areas

  • Information Systems

Cite this

Yukawa, M., & Yamada, I. (2019). A Fixed-Point Analysis of Regularized Dual Averaging under Static Scenarios. In 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings (pp. 207-211). [8659576] (2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/APSIPA.2018.8659576

A Fixed-Point Analysis of Regularized Dual Averaging under Static Scenarios. / Yukawa, Masahiro; Yamada, Isao.

2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 207-211 8659576 (2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings).

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

Yukawa, M & Yamada, I 2019, A Fixed-Point Analysis of Regularized Dual Averaging under Static Scenarios. in 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings., 8659576, 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 207-211, 10th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018, Honolulu, United States, 18/11/12. https://doi.org/10.23919/APSIPA.2018.8659576
Yukawa M, Yamada I. A Fixed-Point Analysis of Regularized Dual Averaging under Static Scenarios. In 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. p. 207-211. 8659576. (2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings). https://doi.org/10.23919/APSIPA.2018.8659576
Yukawa, Masahiro ; Yamada, Isao. / A Fixed-Point Analysis of Regularized Dual Averaging under Static Scenarios. 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 207-211 (2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings).
@inproceedings{e367a4251ddc448b8f9808fbbf3b4068,
title = "A Fixed-Point Analysis of Regularized Dual Averaging under Static Scenarios",
abstract = "In this paper, we analyze the properties of a fixed point of a certain mapping that is implicitly used in each of the regularized dual averaging (RDA) and projection-based RDA (PDA) algorithms. It turns out that, if the loss function has a nonexpansive (1-Lipschltz) gradient such as in the case of a half squared-distance function, RDA converges to a minimizer of the penalized loss function under a restrictive condition. Meanwhile, the fixed point for PDA gives a minimizer of the 'unpenalized' loss function. Some simulation studies are also presented to support the theoretical findings.",
author = "Masahiro Yukawa and Isao Yamada",
year = "2019",
month = "3",
day = "4",
doi = "10.23919/APSIPA.2018.8659576",
language = "English",
series = "2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "207--211",
booktitle = "2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings",

}

TY - GEN

T1 - A Fixed-Point Analysis of Regularized Dual Averaging under Static Scenarios

AU - Yukawa, Masahiro

AU - Yamada, Isao

PY - 2019/3/4

Y1 - 2019/3/4

N2 - In this paper, we analyze the properties of a fixed point of a certain mapping that is implicitly used in each of the regularized dual averaging (RDA) and projection-based RDA (PDA) algorithms. It turns out that, if the loss function has a nonexpansive (1-Lipschltz) gradient such as in the case of a half squared-distance function, RDA converges to a minimizer of the penalized loss function under a restrictive condition. Meanwhile, the fixed point for PDA gives a minimizer of the 'unpenalized' loss function. Some simulation studies are also presented to support the theoretical findings.

AB - In this paper, we analyze the properties of a fixed point of a certain mapping that is implicitly used in each of the regularized dual averaging (RDA) and projection-based RDA (PDA) algorithms. It turns out that, if the loss function has a nonexpansive (1-Lipschltz) gradient such as in the case of a half squared-distance function, RDA converges to a minimizer of the penalized loss function under a restrictive condition. Meanwhile, the fixed point for PDA gives a minimizer of the 'unpenalized' loss function. Some simulation studies are also presented to support the theoretical findings.

UR - http://www.scopus.com/inward/record.url?scp=85063503000&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063503000&partnerID=8YFLogxK

U2 - 10.23919/APSIPA.2018.8659576

DO - 10.23919/APSIPA.2018.8659576

M3 - Conference contribution

AN - SCOPUS:85063503000

T3 - 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings

SP - 207

EP - 211

BT - 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -