• Login
    View Item 
    •   SMARTech Home
    • Georgia Tech Interdisciplinary Research Institutes (IRIs)
    • Transdisciplinary Research Institute for Advancing Data Science (TRIAD)
    • Transdisciplinary Research Institute for Advancing Data Science (TRIAD) Lectures
    • View Item
    •   SMARTech Home
    • Georgia Tech Interdisciplinary Research Institutes (IRIs)
    • Transdisciplinary Research Institute for Advancing Data Science (TRIAD)
    • Transdisciplinary Research Institute for Advancing Data Science (TRIAD) Lectures
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Lecture 5: Inference and Uncertainty Quantification for Noise Matrix Completion

    Thumbnail
    View/Open
    ychen5.mp4 (412.6Mb)
    ychen5_videostream.html (1.136Kb)
    transcript.txt (38.29Kb)
    thumbnail.jpg (46.71Kb)
    Date
    2019-09-05
    Author
    Chen, Yuxin
    Metadata
    Show full item record
    Abstract
    Noisy matrix completion aims at estimating a low-rank matrix given only partial and corrupted entries. Despite substantial progress in designing efficient estimation algorithms, it remains largely unclear how to assess the uncertainty of the obtained estimates and how to perform statistical inference on the unknown matrix (e.g. constructing a valid and short confidence interval for an unseen entry). This talk takes a step towards inference and uncertainty quantification for noisy matrix completion. We develop a simple procedure to compensate for the bias of the widely used convex and nonconvex estimators. The resulting de-biased estimators admit nearly precise non-asymptotic distributional characterizations, which in turn enable optimal construction of confidence intervals / regions for, say, the missing entries and the low-rank factors. Our inferential procedures do not rely on sample splitting, thus avoiding unnecessary loss of data efficiency. As a byproduct, we obtain a sharp characterization of the estimation accuracy of our de-biased estimators, which, to the best of our knowledge, are the first tractable algorithms that provably achieve full statistical efficiency (including the preconstant). The analysis herein is built upon the intimate link between convex and nonconvex optimization. This is joint work with Cong Ma, Yuling Yan, Yuejie Chi, and Jianqing Fan.
    URI
    http://hdl.handle.net/1853/61861
    Collections
    • Transdisciplinary Research Institute for Advancing Data Science (TRIAD) Lectures [16]

    Browse

    All of SMARTechCommunities & CollectionsDatesAuthorsTitlesSubjectsTypesThis CollectionDatesAuthorsTitlesSubjectsTypes

    My SMARTech

    Login

    Statistics

    View Usage StatisticsView Google Analytics Statistics
    facebook instagram twitter youtube
    • My Account
    • Contact us
    • Directory
    • Campus Map
    • Support/Give
    • Library Accessibility
      • About SMARTech
      • SMARTech Terms of Use
    Georgia Tech Library266 4th Street NW, Atlanta, GA 30332
    404.894.4500
    • Emergency Information
    • Legal and Privacy Information
    • Human Trafficking Notice
    • Accessibility
    • Accountability
    • Accreditation
    • Employment
    © 2020 Georgia Institute of Technology