There has been significant study on the sample complexity of testing properties of distributions over large domains. For many properties, it is known that the sample complexity can be substantially smaller than the domain size. For example, over a domain of size n, distinguishing the uniform distribution from distributions that are far from uniform in ℓ1distance uses only O(n−−√) samples. However, the picture is very different in the presence of arbitrary noise, even when the amount of noise is quite small. In this case, one must distinguish if samples are coming from a distribution that is ϵclose to uniform from the case where the distribution is (1−ϵ)far from uniform. The latter task requires nearly linear in n samples (Valiant, 2008; Valiant and Valiant, 2017a). In this work, we present a noise model that on one hand is more tractable for the testing problem, and on the other hand represents a rich class of noise families. In our model, the noisy distribution is a mixture of the original distribution and noise, where the latter is known to the tester either explicitly or via sample access; the form of the noise is also known \emph{a priori}. Focusing on the identity and closeness testing problems leads to the following mixture testing question: Given samples of distributions p,q1,q2, can we test if p is a mixture of q1 and q2? We consider this general question in various scenarios that differ in terms of how the tester can access the distributions, and show that indeed this problem is more tractable. Our results show that the sample complexity of our testers are exactly the same as for the classical nonmixture case.
more »
« less
Testing Mixtures of Discrete Distributions
There has been significant study on the sample complexity of testing properties of distributions over large domains. For many properties, it is known that the sample complexity can be substantially smaller than the domain size. For example, over a domain of size n, distinguishing the uniform distribution from distributions that are far from uniform in ℓ1distance uses only O(n−−√) samples. However, the picture is very different in the presence of arbitrary noise, even when the amount of noise is quite small. In this case, one must distinguish if samples are coming from a distribution that is ϵclose to uniform from the case where the distribution is (1−ϵ)far from uniform. The latter task requires nearly linear in n samples (Valiant, 2008; Valiant and Valiant, 2017a). In this work, we present a noise model that on one hand is more tractable for the testing problem, and on the other hand represents a rich class of noise families. In our model, the noisy distribution is a mixture of the original distribution and noise, where the latter is known to the tester either explicitly or via sample access; the form of the noise is also known \emph{a priori}. Focusing on the identity and closeness testing problems leads to the following mixture testing question: Given samples of distributions p,q1,q2, can we test if p is a mixture of q1 and q2? We consider this general question in various scenarios that differ in terms of how the tester can access the distributions, and show that indeed this problem is more tractable. Our results show that the sample complexity of our testers are exactly the same as for the classical nonmixture case.
more »
« less
 NSFPAR ID:
 10108396
 Date Published:
 Journal Name:
 Proceedings of the ThirtySecond Conference on Learning Theory (PMLR)
 Volume:
 99
 Page Range / eLocation ID:
 83114
 Format(s):
 Medium: X
 Sponsoring Org:
 National Science Foundation
More Like this


We study the problem of testing identity against a given distribution with a focus on the high confidence regime. More precisely, given samples from an unknown distribution p over n elements, an explicitly given distribution q, and parameters 0< epsilon, delta < 1, we wish to distinguish, with probability at least 1delta, whether the distributions are identical versus epsilonfar in total variation distance. Most prior work focused on the case that delta = Omega(1), for which the sample complexity of identity testing is known to be Theta(sqrt{n}/epsilon^2). Given such an algorithm, one can achieve arbitrarily small values of delta via blackbox amplification, which multiplies the required number of samples by Theta(log(1/delta)). We show that blackbox amplification is suboptimal for any delta = o(1), and give a new identity tester that achieves the optimal sample complexity. Our new upper and lower bounds show that the optimal sample complexity of identity testing is Theta((1/epsilon^2) (sqrt{n log(1/delta)} + log(1/delta))) for any n, epsilon, and delta. For the special case of uniformity testing, where the given distribution is the uniform distribution U_n over the domain, our new tester is surprisingly simple: to test whether p = U_n versus d_{TV} (p, U_n) >= epsilon, we simply threshold d_{TV}({p^}, U_n), where {p^} is the empirical probability distribution. The fact that this simple "plugin" estimator is sampleoptimal is surprising, even in the constant delta case. Indeed, it was believed that such a tester would not attain sublinear sample complexity even for constant values of epsilon and delta. An important contribution of this work lies in the analysis techniques that we introduce in this context. First, we exploit an underlying strong convexity property to bound from below the expectation gap in the completeness and soundness cases. Second, we give a new, fast method for obtaining provably correct empirical estimates of the true worstcase failure probability for a broad class of uniformity testing statistics over all possible input distributions  including all previously studied statistics for this problem. We believe that our novel analysis techniques will be useful for other distribution testing problems as well.more » « less

Uniformity testing is one of the most wellstudied problems in property testing, with many known test statistics, including ones based on counting collisions, singletons, and the empirical TV distance. It is known that the optimal sample complexity to distinguish the uniform distribution on m elements from any ϵfar distribution with 1−δ probability is n=Θ(mlog(1/δ)√ϵ2+log(1/δ)ϵ2), which is achieved by the empirical TV tester. Yet in simulation, these theoretical analyses are misleading: in many cases, they do not correctly rank order the performance of existing testers, even in an asymptotic regime of all parameters tending to 0 or ∞. We explain this discrepancy by studying the \emph{constant factors} required by the algorithms. We show that the collisions tester achieves a sharp maximal constant in the number of standard deviations of separation between uniform and nonuniform inputs. We then introduce a new tester based on the Huber loss, and show that it not only matches this separation, but also has tails corresponding to a Gaussian with this separation. This leads to a sample complexity of (1+o(1))mlog(1/δ)√ϵ2 in the regime where this term is dominant, unlike all other existing testers.more » « less

We give the first testerlearner for halfspaces that succeeds universally over a wide class of structured distributions. Our universal testerlearner runs in fully polynomial time and has the following guarantee: the learner achieves error O(opt)+ϵ on any labeled distribution that the tester accepts, and moreover, the tester accepts whenever the marginal is any distribution that satisfies a Poincare inequality. In contrast to prior work on testable learning, our tester is not tailored to any single target distribution but rather succeeds for an entire target class of distributions. The class of Poincare distributions includes all strongly logconcave distributions, and, assuming the KannanLovaszSimonovits (KLS) conjecture, includes all logconcave distributions. In the special case where the label noise is known to be Massart, our testerlearner achieves error opt+ϵ while accepting all logconcave distributions unconditionally (without assuming KLS).Our tests rely on checking hypercontractivity of the unknown distribution using a sumofsquares (SOS) program, and crucially make use of the fact that Poincare distributions are certifiably hypercontractive in the SOS framework.more » « less

We show how any PAC learning algorithm that works under the uniform distribution can be transformed, in a blackbox fashion, into one that works under an arbitrary and unknown distribution D. The efficiency of our transformation scales with the inherent complexity of D, running in (n, (md)d) time for distributions over n whose pmfs are computed by depthd decision trees, where m is the sample complexity of the original algorithm. For monotone distributions our transformation uses only samples from D, and for general ones it uses subcube conditioning samples. A key technical ingredient is an algorithm which, given the aforementioned access to D, produces an optimal decision tree decomposition of D: an approximation of D as a mixture of uniform distributions over disjoint subcubes. With this decomposition in hand, we run the uniformdistribution learner on each subcube and combine the hypotheses using the decision tree. This algorithmic decomposition lemma also yields new algorithms for learning decision tree distributions with runtimes that exponentially improve on the prior state of the art—results of independent interest in distribution learning.more » « less