Testing symmetric properties of distributions

Paul Valiant

Abstract

We introduce the notion of a Canonical Tester for a class of properties on distributions, that is, a tester strong and general enough that "a distribution property in the class is testable if and only if the Canonical Tester tests it". We construct a Canonical Tester for the class of symmetric properties of one or two distributions, satisfying a certain weak continuity condition. Analyzing the performance of the Canonical Tester on specific properties resolves several open problems, establishing lower bounds that match known upper bounds: we show that distinguishing between entropy < a or > p on distributions over [n] requires nc/P-O(1) samples, and distinguishing whether a pair of distributions has statistical distance < a or > 0 requires n1-o(1) samples. Our techniques also resolve a conjecture about a property that our Canonical Tester does not apply to: distinguishing identical distributions from those with statistical distance > 0 requires Q(n2/3) samples.
BibTeX
@article{valiant2011testing,
  author = {Paul Valiant},
  title = {{Testing symmetric properties of distributions}},
  journal = {SIAM Journal on Computing},
  year = {2011},
  url = {https://openreview.net/forum?id=vsk-sDH7VzN},
}

Loading related content...

Figure