Dr. Qiang Wu

Professor

Dr. Qiang Wu
Email
615-898-2053
Room 322A, Kirksey Old Main (KOM)
MTSU Box 34, Murfreesboro, TN 37132
capone.mtsu.edu/qwu/

Departments / Programs

Degree Information

  • PHD, City University of Hong Kong (2005)
  • MS, Beijing Normal University (2000)
  • BS, Yantai University (1997)

Areas of Expertise

  • Machine learning, deep learning
  • Big data, distributed learning
  • High dimensional data mining
  • Computational harmonic analysis
  • Actuarial science

Biography

I earned my Ph.D. in applied mathematics in 2005 from City University of Hong Kong with a resarch focus on machine learning theory and received postdoctoral training in machine learning and statistics at Duke University from 2005 to 2008. I attained the Associateship designation from the Society of Actuaries in 2014.

I joined Middle Tennessee State University in 2011 and was promoted to full professor in 2020.  I am the director of the Data Science Master of Science and Graduate Certificate programs and a faulty member of the Computational and Data Science Ph.D. program.

Publications

  • Hongwei Sun and Qiang Wu. Optimal rates of distributed regression with imperfect kernels. JMLR, 22(171):1-34, 2021. [journal link]
  • X. Guo, T. Hu and Q. Wu, Distributed Minimum Error Entropy Algorithms JMLR, 21(126):1-31, 2020. [
Read More »
  • Hongwei Sun and Qiang Wu. Optimal rates of distributed regression with imperfect kernels. JMLR, 22(171):1-34, 2021. [journal link]
  • X. Guo, T. Hu and Q. Wu, Distributed Minimum Error Entropy Algorithms JMLR, 21(126):1-31, 2020. [journal link]
  • Y. Feng and Q. Wu, Learning under (1+ε)-moment conditions, Applied and Computational Harmonic Analysis, 49 (2020), 495-520. [journal link]
  • T. Hu, Q. Wu, and D.-X. Zhou. Distributed kernel gradient descent algorithm for minimum error entropy principle. Applied and Computational Harmonic Analysis, 49:1 (2020), 229-256. [journal link]
  • Z.-C. Guo, L. Shi, and Qiang Wu. Learning theory of distributed regression with bias corrected regularization kernel network. Journal of Machine Learning Research, 18(118):1-25, 2017. [journal link]
  • T. Hu, Qiang Wu and D.-X. Zhou, Convergence of gradient descent for minimum error entropy principle in linear regression, IEEE Transactions on Signal Processing, 64(24):6571-6579, 2016. [journal link]
  • J. Fan, T. Hu, Qiang Wu, and D.-X. Zhou. Consistency analysis of minimum error entropy algorithm. Applied and Computational Harmonic Analysis, 41:164-189, 2016. [journal link]
  • H. Sun and Qiang Wu. Sparse Representation in Kernel Machines. IEEE Transactions on Neural Networks and Learning Systems, 26(10):2576-2582, 2015. [journal link]
  • T. Hu, J. Fan, Qiang Wu, and D.-X. Zhou. Learning theory approach to minimum error entropy criterion. Journal of Machine Learning Research, 14:377-397, 2013. [journal link]
  • Qiang Wu. Regularization Networks with Indefinite Kernels, Journal of Approximation Theory, 166:1-18, 2013. [journal link]
  • J. M. Hughes, D. Mao, D. N. Rockmore, Y. Wang and Qiang Wu. Empirical mode decomposition analysis for visual stylometry. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(11):2147-2157, 2012.  [journal link]
  • H. Sun and Qiang Wu. Least square regression with indefinite kernels and coefficient regularization. Applied and Computational Harmonica Analysis, 30(1):96-109, 2011. [journal link]
  • J. Guinney, Qiang Wu, and S. Mukherjee. Estimating variable structure and dependence in multi-task learning via gradients. Machine Learning, 83(3):265-287, 2011. [journal link]

 

Full publication list on my webpage or google scholar.

« Read Less