IDEAS home Printed from https://ideas.repec.org/a/spr/snopef/v2y2021i2d10.1007_s43069-021-00059-y.html
   My bibliography  Save this article

Randomized Smoothing Variance Reduction Method for Large-Scale Non-smooth Convex Optimization

Author

Listed:
  • Wenjie Huang

    (The Chinese University of Hong Kong)

  • Xun Zhang

    (National University of Singapore)

Abstract

We consider a new method for minimizing the average of a large number of non-smooth and convex functions. Such a problem often arises in typical machine learning problems, but is computationally challenging. We apply an implementable randomized smoothing method and propose a multistage scheme to progressively reduce the variance of the gradient estimator of the smoothed functions. Our algorithm achieves a linear convergence rate. Both its time complexity and gradient complexity are superior to the current standard algorithms for non-smooth minimization as well as subgradient-based algorithms. Besides, our algorithm works well without the error-bound condition on the minimizing sequence as well as the commonly imposed (but strong) smoothness and strongly convexity condition. We show that our algorithm has wide applications in optimization and machine learning problems. As an illustrative example, we demonstrate experimentally that our algorithm performs well on large-scale ranking problems and risk-aware portfolio optimization problems.

Suggested Citation

  • Wenjie Huang & Xun Zhang, 2021. "Randomized Smoothing Variance Reduction Method for Large-Scale Non-smooth Convex Optimization," SN Operations Research Forum, Springer, vol. 2(2), pages 1-28, June.
    • Handle: RePEc:spr:snopef:v:2:y:2021:i:2:d:10.1007_s43069-021-00059-y
    DOI: 10.1007/s43069-021-00059-y
    as

    Download full text from publisher

    File URL: http://link.springer.com/10.1007/s43069-021-00059-y
    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/s43069-021-00059-y?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. Hong Chen & Fangchao He & Zhibin Pan, 2012. "Approximation Analysis of Gradient Descent Algorithm for Bipartite Ranking," Journal of Applied Mathematics, Hindawi, vol. 2012, pages 1-13, July.
    2. Jie Shen & Li-Ping Pang & Dan Li, 2013. "An Approximate Quasi-Newton Bundle-Type Method for Nonsmooth Optimization," Abstract and Applied Analysis, Hindawi, vol. 2013, pages 1-7, April.
    3. Robert Tibshirani & Michael Saunders & Saharon Rosset & Ji Zhu & Keith Knight, 2005. "Sparsity and smoothness via the fused lasso," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 67(1), pages 91-108, February.
    4. NESTEROV, Yu., 2005. "Smooth minimization of non-smooth functions," LIDAM Reprints CORE 1819, Université catholique de Louvain, Center for Operations Research and Econometrics (CORE).
    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. Yunmei Chen & Xiaojing Ye & Wei Zhang, 2020. "Acceleration techniques for level bundle methods in weakly smooth convex constrained optimization," Computational Optimization and Applications, Springer, vol. 77(2), pages 411-432, November.
    2. Prater, Ashley & Shen, Lixin & Suter, Bruce W., 2015. "Finding Dantzig selectors with a proximity operator based fixed-point algorithm," Computational Statistics & Data Analysis, Elsevier, vol. 90(C), pages 36-46.
    3. Tutz, Gerhard & Pößnecker, Wolfgang & Uhlmann, Lorenz, 2015. "Variable selection in general multinomial logit models," Computational Statistics & Data Analysis, Elsevier, vol. 82(C), pages 207-222.
    4. Mkhadri, Abdallah & Ouhourane, Mohamed, 2013. "An extended variable inclusion and shrinkage algorithm for correlated variables," Computational Statistics & Data Analysis, Elsevier, vol. 57(1), pages 631-644.
    5. Yize Zhao & Matthias Chung & Brent A. Johnson & Carlos S. Moreno & Qi Long, 2016. "Hierarchical Feature Selection Incorporating Known and Novel Biological Information: Identifying Genomic Features Related to Prostate Cancer Recurrence," Journal of the American Statistical Association, Taylor & Francis Journals, vol. 111(516), pages 1427-1439, October.
    6. Francis X. Diebold & Kamil Yilmaz, 2016. "Trans-Atlantic Equity Volatility Connectedness: U.S. and European Financial Institutions, 2004–2014," Journal of Financial Econometrics, Oxford University Press, vol. 14(1), pages 81-127.
    7. Jian Guo & Elizaveta Levina & George Michailidis & Ji Zhu, 2010. "Pairwise Variable Selection for High-Dimensional Model-Based Clustering," Biometrics, The International Biometric Society, vol. 66(3), pages 793-804, September.
    8. Franck Rapaport & Christina Leslie, 2010. "Determining Frequent Patterns of Copy Number Alterations in Cancer," PLOS ONE, Public Library of Science, vol. 5(8), pages 1-10, August.
    9. Lu Tang & Ling Zhou & Peter X. K. Song, 2019. "Fusion learning algorithm to combine partially heterogeneous Cox models," Computational Statistics, Springer, vol. 34(1), pages 395-414, March.
    10. Young‐Geun Choi & Lawrence P. Hanrahan & Derek Norton & Ying‐Qi Zhao, 2022. "Simultaneous spatial smoothing and outlier detection using penalized regression, with application to childhood obesity surveillance from electronic health records," Biometrics, The International Biometric Society, vol. 78(1), pages 324-336, March.
    11. Molly C. Klanderman & Kathryn B. Newhart & Tzahi Y. Cath & Amanda S. Hering, 2020. "Fault isolation for a complex decentralized waste water treatment facility," Journal of the Royal Statistical Society Series C, Royal Statistical Society, vol. 69(4), pages 931-951, August.
    12. Wang, Li-Yu & Park, Cheolwoo & Yeon, Kyupil & Choi, Hosik, 2017. "Tracking concept drift using a constrained penalized regression combiner," Computational Statistics & Data Analysis, Elsevier, vol. 108(C), pages 52-69.
    13. Tomáš Plíhal, 2021. "Scheduled macroeconomic news announcements and Forex volatility forecasting," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 40(8), pages 1379-1397, December.
    14. Dirk Lorenz & Marc Pfetsch & Andreas Tillmann, 2014. "An infeasible-point subgradient method using adaptive approximate projections," Computational Optimization and Applications, Springer, vol. 57(2), pages 271-306, March.
    15. Loann David Denis Desboulets, 2018. "A Review on Variable Selection in Regression Analysis," Econometrics, MDPI, vol. 6(4), pages 1-27, November.
    16. Murat Genç & M. Revan Özkale, 2021. "Usage of the GO estimator in high dimensional linear models," Computational Statistics, Springer, vol. 36(1), pages 217-239, March.
    17. Aytug, Haldun & Sayın, Serpil, 2012. "Exploring the trade-off between generalization and empirical errors in a one-norm SVM," European Journal of Operational Research, Elsevier, vol. 218(3), pages 667-675.
    18. Hwang, Youngdeok & Kim, Hang J. & Chang, Won & Yeo, Kyongmin & Kim, Yongku, 2019. "Bayesian pollution source identification via an inverse physics model," Computational Statistics & Data Analysis, Elsevier, vol. 134(C), pages 76-92.
    19. Victor Chernozhukov & Christian Hansen & Yuan Liao, 2015. "A lava attack on the recovery of sums of dense and sparse signals," CeMMAP working papers CWP56/15, Centre for Microdata Methods and Practice, Institute for Fiscal Studies.
    20. Luu, Tung Duy & Fadili, Jalal & Chesneau, Christophe, 2019. "PAC-Bayesian risk bounds for group-analysis sparse regression by exponential weighting," Journal of Multivariate Analysis, Elsevier, vol. 171(C), pages 209-233.

    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:snopef:v:2:y:2021:i:2:d:10.1007_s43069-021-00059-y. 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.