Czumaj, A., Adamaszek, M. and Sohler, C. (2010) Testing Monotone Continuous Distributions on High-dimensional Real Cubes. In: 21st ACM-SIAM Symposium on Discrete Algorithms (SODA'10), Austin, Texas,.

PDF Download (699Kb)

Abstract

We study the task of testing properties of probability
distributions. We consider a scenario in which we
have access to independent samples of an unknown
distribution D with in�nite (perhaps even uncountable)
support. Our goal is to test whether D has a given
property or it is "-far from it (in the statistical distance,
with the L1-distance measure).
It is not di�cult to see that for many natural dis-
tributions on in�nite or uncountable domains, no test-
ing algorithm can exist and the central objective of our
study is to understand if there are any nontrivial dis-
tributions that can be e�ciently tested. For example,
it is easy to see that there is no testing algorithm that
tests if a given probability distribution on [0; 1] is uni-
form. We show however, that if some additional infor-
mation about the input distribution is known, testing
uniform distribution is possible. We extend the recent
result about testing uniformity for monotone distribu-
tions on Boolean n-dimensional cubes by Rubinfeld and
Servedio (STOC'2005) to the case of continuous [0; 1]n
cubes. We show that if a distribution D on [0; 1]n is
monotone, then one can test if D is uniform with the
sample complexity O(n="2). This result is optimal up
to a polylogarithmic factor.

Actions (login required)