5
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Robust Mean Estimation under Coordinate-level Corruption

      Preprint

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Data corruption, systematic or adversarial, may skew statistical estimation severely. Recent work provides computationally efficient estimators that nearly match the information-theoretic optimal statistic. Yet the corruption model they consider measures sample-level corruption and is not fine-grained enough for many real-world applications. In this paper, we propose a coordinate-level metric of distribution shift over high-dimensional settings with n coordinates. We introduce and analyze robust mean estimation techniques against an adversary who may hide individual coordinates of samples while being bounded by that metric. We show that for structured distribution settings, methods that leverage structure to fill in missing entries before mean estimation can improve the estimation accuracy by a factor of approximately n compared to structure-agnostic methods. We also leverage recent progress in matrix completion to obtain estimators for recovering the true mean of the samples in settings of unknown structure. We demonstrate with real-world data that our methods can capture the dependencies across attributes and provide accurate mean estimation even in high-magnitude corruption settings.

          Related collections

          Author and article information

          Journal
          10 February 2020
          Article
          2002.04137
          0a423055-b343-4300-8881-4fa08983d4e9

          http://arxiv.org/licenses/nonexclusive-distrib/1.0/

          History
          Custom metadata
          68T01, 62F99
          16 pages, 3 figures
          cs.LG stat.ML

          Machine learning,Artificial intelligence
          Machine learning, Artificial intelligence

          Comments

          Comment on this article