arxivst stuff from arxiv that you should probably bookmark

Resilience: A Criterion for Learning in the Presence of Arbitrary Outliers

Abstract · Mar 15, 2017 05:43 ·

cs-lg cs-ai cs-cc cs-cr stat-ml

Arxiv Abstract

  • Jacob Steinhardt
  • Moses Charikar
  • Gregory Valiant

We introduce a criterion, resilience, which allows properties of a dataset (such as its mean or best low rank approximation) to be robustly computed, even in the presence of a large fraction of arbitrary additional data. Resilience is a weaker condition than most other properties considered so far in the literature, and yet enables robust estimation in a broader variety of settings, including the previously unstudied problem of robust mean estimation in $\ell_p$-norms.

Read the paper (pdf) »