IDEAS home Printed from https://ideas.repec.org/a/spr/coopap/v70y2018i2d10.1007_s10589-018-0002-6.html
   My bibliography  Save this article

A nonconvex formulation for low rank subspace clustering: algorithms and convergence analysis

Author

Listed:
  • Hao Jiang

    (Johns Hopkins University)

  • Daniel P. Robinson

    (Johns Hopkins University)

  • René Vidal

    (Johns Hopkins University)

  • Chong You

    (Johns Hopkins University)

Abstract

We consider the problem of subspace clustering with data that is potentially corrupted by both dense noise and sparse gross errors. In particular, we study a recently proposed low rank subspace clustering approach based on a nonconvex modeling formulation. This formulation includes a nonconvex spectral function in the objective function that makes the optimization task challenging, e.g., it is unknown whether the alternating direction method of multipliers (ADMM) framework proposed to solve the nonconvex model formulation is provably convergent. In this paper, we establish that the spectral function is differentiable and give a formula for computing the derivative. Moreover, we show that the derivative of the spectral function is Lipschitz continuous and provide an explicit value for the Lipschitz constant. These facts are then used to provide a lower bound for how the penalty parameter in the ADMM method should be chosen. As long as the penalty parameter is chosen according to this bound, we show that the ADMM algorithm computes iterates that have a limit point satisfying first-order optimality conditions. We also present a second strategy for solving the nonconvex problem that is based on proximal gradient calculations. The convergence and performance of the algorithms is verified through experiments on real data from face and digit clustering and motion segmentation.

Suggested Citation

  • Hao Jiang & Daniel P. Robinson & René Vidal & Chong You, 2018. "A nonconvex formulation for low rank subspace clustering: algorithms and convergence analysis," Computational Optimization and Applications, Springer, vol. 70(2), pages 395-418, June.
  • Handle: RePEc:spr:coopap:v:70:y:2018:i:2:d:10.1007_s10589-018-0002-6
    DOI: 10.1007/s10589-018-0002-6
    as

    Download full text from publisher

    File URL: http://link.springer.com/10.1007/s10589-018-0002-6
    File Function: Abstract
    Download Restriction: Access to the full text of the articles in this series is restricted.

    File URL: https://libkey.io/10.1007/s10589-018-0002-6?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Kristian Bredies & Dirk A. Lorenz & Stefan Reiterer, 2015. "Minimization of Non-smooth, Non-convex Functionals by Iterative Thresholding," Journal of Optimization Theory and Applications, Springer, vol. 165(1), pages 78-112, April.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Kai Tu & Haibin Zhang & Huan Gao & Junkai Feng, 2020. "A hybrid Bregman alternating direction method of multipliers for the linearly constrained difference-of-convex problems," Journal of Global Optimization, Springer, vol. 76(4), pages 665-693, April.
    2. Peng, Bo & Xu, Hong-Kun, 2020. "Proximal methods for reweighted lQ-regularization of sparse signal recovery," Applied Mathematics and Computation, Elsevier, vol. 386(C).
    3. Daria Ghilli & Karl Kunisch, 2019. "On a Monotone Scheme for Nonconvex Nonsmooth Optimization with Applications to Fracture Mechanics," Journal of Optimization Theory and Applications, Springer, vol. 183(2), pages 609-641, November.
    4. Daria Ghilli & Karl Kunisch, 2019. "On monotone and primal-dual active set schemes for $$\ell ^p$$ ℓ p -type problems, $$p \in (0,1]$$ p ∈ ( 0 , 1 ]," Computational Optimization and Applications, Springer, vol. 72(1), pages 45-85, January.
    5. Yaohua Hu & Chong Li & Kaiwen Meng & Xiaoqi Yang, 2021. "Linear convergence of inexact descent method and inexact proximal gradient algorithms for lower-order regularization problems," Journal of Global Optimization, Springer, vol. 79(4), pages 853-883, April.
    6. Victor A. Kovtunenko & Karl Kunisch, 2022. "Shape Derivative for Penalty-Constrained Nonsmooth–Nonconvex Optimization: Cohesive Crack Problem," Journal of Optimization Theory and Applications, Springer, vol. 194(2), pages 597-635, August.
    7. Carolin Natemeyer & Daniel Wachsmuth, 2021. "A proximal gradient method for control problems with non-smooth and non-convex control cost," Computational Optimization and Applications, Springer, vol. 80(2), pages 639-677, November.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:spr:coopap:v:70:y:2018:i:2:d:10.1007_s10589-018-0002-6. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.springer.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.