Projection-based dual averaging for stochastic sparse optimization

Asahi Ushio, Masahiro Yukawa

    研究成果: Conference contribution

    3 引用 (Scopus)

    抜粋

    We present a variant of the regularized dual averaging (RDA) algorithm for stochastic sparse optimization. Our approach differs from the previous studies of RDA in two respects. First, a sparsity-promoting metric is employed, originated from the proportionate-type adaptive filtering algorithms. Second, the squared-distance function to a closed convex set is employed as a part of the objective functions. In the particular application of online regression, the squared-distance function is reduced to a normalized version of the typical squared-error (least square) function. The two differences yield a better sparsity-seeking capability, leading to improved convergence properties. Numerical examples show the advantages of the proposed algorithm over the existing methods including ADAGRAD and adaptive proximal forward-backward splitting (APFBS).

    元の言語English
    ホスト出版物のタイトル2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings
    出版者Institute of Electrical and Electronics Engineers Inc.
    ページ2307-2311
    ページ数5
    ISBN(電子版)9781509041176
    DOI
    出版物ステータスPublished - 2017 6 16
    イベント2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - New Orleans, United States
    継続期間: 2017 3 52017 3 9

    Other

    Other2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017
    United States
    New Orleans
    期間17/3/517/3/9

    ASJC Scopus subject areas

    • Software
    • Signal Processing
    • Electrical and Electronic Engineering

    フィンガープリント Projection-based dual averaging for stochastic sparse optimization' の研究トピックを掘り下げます。これらはともに一意のフィンガープリントを構成します。

  • これを引用

    Ushio, A., & Yukawa, M. (2017). Projection-based dual averaging for stochastic sparse optimization. : 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings (pp. 2307-2311). [7952568] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2017.7952568