Robustness Meets Algorithms (Invited Talk)

Author Ankur Moitra

Thumbnail PDF


  • Filesize: 156 kB
  • 1 pages

Document Identifiers

Author Details

Ankur Moitra
  • Department of Mathematics, MIT, Cambridge, Massachusetts, USA

Cite AsGet BibTex

Ankur Moitra. Robustness Meets Algorithms (Invited Talk). In 16th Scandinavian Symposium and Workshops on Algorithm Theory (SWAT 2018). Leibniz International Proceedings in Informatics (LIPIcs), Volume 101, p. 3:1, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2018)


In every corner of machine learning and statistics, there is a need for estimators that work not just in an idealized model but even when their assumptions are violated. Unfortunately in high-dimensions, being provably robust and efficiently computable are often at odds with each other. In this talk, we give the first efficient algorithm for estimating the parameters of a high-dimensional Gaussian which is able to tolerate a constant fraction of corruptions that is independent of the dimension. Prior to our work, all known estimators either needed time exponential in the dimension to compute, or could tolerate only an inverse polynomial fraction of corruptions. Not only does our algorithm bridge the gap between robustness and algorithms, it turns out to be highly practical in a variety of settings.

Subject Classification

ACM Subject Classification
  • Theory of computation → Design and analysis of algorithms
  • Computing methodologies → Machine learning algorithms
  • robust estimators
  • machine learning algorithms


  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    PDF Downloads
Questions / Remarks / Feedback

Feedback for Dagstuhl Publishing

Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail