Efficient Statistics, in High Dimensions, from Truncated Samples
Author(s)
Daskalakis, Constantinos; Gouleakis, Themis; Tzamos, Chistos; Zampetakis, Manolis
DownloadSubmitted version (502.6Kb)
Terms of use
Metadata
Show full item recordAbstract
We provide an efficient algorithm for the classical problem, going back to Galton, Pearson,and Fisher, of estimating, with arbitrary accuracy the parameters of a multivariate normal distribution from truncated samples. Truncated samples from ad-variate normal N(μ,Σ) means a samples is only revealed if it falls in some subset S⊆Rd; otherwise the samples are hidden and their count in proportion to the revealed samples is also hidden. We show that the meanμand covariance matrixΣcan be estimated with arbitrary accuracy in polynomial-time, as long as we have oracle access to S, and S has non-trivial measure under the unknown d-variate normal distribution. Additionally we show that without oracle access to S, any non-trivial estimation is impossible.
Date issued
2018-10Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence LaboratoryPublisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Daskalakis, Constantinos, Gouleakis, Themis, Tzamos, Chistos and Zampetakis, Manolis. 2018. "Efficient Statistics, in High Dimensions, from Truncated Samples."
Version: Original manuscript