@inproceedings{27dd2b1c4f3a476485bc7b17c4635823,

title = "Approximating and testing k-histogram distributions in sub-linear time",

abstract = "A discrete distribution p, over [n], is a k histogram if its probability distribution function can be represented as a piece-wise constant function with k pieces. Such a function is represented by a list of k intervals and k corresponding values. We consider the following problem: given a collection of samples from a distribution p, find a k-histogram that (approximately) minimizes the ℓ 2 distance to the distribution p. We give time and sample efficient algorithms for this problem. We further provide algorithms that distinguish distributions that have the property of being a k-histogram from distributions that are ε-far from any k-histogram in the ℓ 2 distance and ℓ 2 distance respectively.",

keywords = "distribution, histogram, property testing",

author = "Piotr Indyk and Reut Levi and Ronitt Rubinfeld",

year = "2012",

doi = "10.1145/2213556.2213561",

language = "אנגלית",

isbn = "9781450312486",

series = "Proceedings of the ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems",

pages = "15--21",

booktitle = "PODS '12 - Proceedings of the 31st Symposium on Principles of Database Systems",

note = "31st ACM SIGMOD-SIGACT-SIGART Symposium on Principles of Database Systems, PODS '12 ; Conference date: 21-05-2012 Through 23-05-2012",

}