Testing Similar Means
We consider the problem of testing a basic property of collections of distributions: having similar means. Namely, the algorithm should accept collections of distributions in which all distributions have means that do not differ by more than some given parameter, and should reject collections that are relatively far from having this property. By ‘far’ we mean that it is necessary to modify the distributions in a relatively significant manner (measured according to the ℓ1 distance averaged over the distributions) so as to obtain the property. We study this problem in two models. In the first model (the query model) the algorithm may ask for samples from any distribution of its choice, and in the second model (the sampling model) the distributions from which it gets samples are selected randomly. We provide upper and lower bounds in both models. In particular, in the query model, the complexity of the problem is polynomial in 1/ε (where ε is the given distance parameter). While in the sampling model, the complexity grows roughly as m 1 − poly(ε), where m is the number of distributions.
KeywordsSuccess Probability Sample Complexity Basic Algorithm Chebyshev Polynomial Sampling Model
Unable to display preview. Download preview PDF.
- 1.Batu, T., Fortnow, L., Fischer, E., Kumar, R., Rubinfeld, R., White, P.: Testing random variables for independence and identity. In: Proceedings of FOCS, pp. 442–451 (2001)Google Scholar
- 2.Batu, T., Fortnow, L., Rubinfeld, R., Smith, W.D., White, P.: Testing that distributions are close. In: Proceedings of FOCS, pp. 259–269 (2000)Google Scholar
- 3.Chebyshev, P.L.: Théorie des mécanismes connus sous le nom de parallélogrammes. Mémoires des Savants étrangers présentés â l’Académie de Saint-Pétersbourg 7, 539–586 (1854)Google Scholar
- 5.Goldreich, O., Ron, D.: Property testing in bounded degree graphs. Algorithmica, 302–343 (2002)Google Scholar
- 6.Larsen, R.J., Marx, M.L.: An introduction to mathematical statistics and its applications, vol. 1. Pearson Prentice Hall (2006)Google Scholar
- 7.Levi, R., Ron, D., Rubinfeld, R.: Testing properties of collections of distributions. Technical Report TR10-157, Electronic Colloquium on Computational Complexity (ECCC) (2010)Google Scholar
- 8.Levi, R., Ron, D., Rubinfeld, R.: Testing properties of collections of distributions. In: Proceedings of ICS, pp. 179–194 (2011); See also ECCC TR10-157Google Scholar
- 9.Levi, R., Ron, D., Rubinfeld, R.: Testing similar means. Technical Report TR12-055, Electronic Colloquium on Computational Complexity (ECCC) (2012)Google Scholar
- 10.Mendenhall, W., Beaver, R.J., Beaver, B.M.: Introduction to probability and statistics. Brooks/Cole, Cengage Learning (2009)Google Scholar
- 12.Student. The probable error of a mean. Biometrika 6, 1–25 (1908)Google Scholar
- 13.Valiant, G., Valiant, P.: Estimating the unseen: an n/log(n)-sample estimator for entropy and support size, shown optimal via new CLTs. In: Proceedings of STOC, pp. 685–694 (2011)Google Scholar
- 14.Valiant, P.: Testing symmetric properties of distributions. In: Proceedings of STOC, pp. 383–392 (2008)Google Scholar