FastMMD: Ensemble of Circular Discrepancy for Efficient Two-Sample Test
نویسندگان
چکیده
منابع مشابه
FastMMD: Ensemble of Circular Discrepancy for Efficient Two-Sample Test
The maximum mean discrepancy (MMD) is a recently proposed test statistic for the two-sample test. Its quadratic time complexity, however, greatly hampers its availability to large-scale applications. To accelerate the MMD calculation, in this study we propose an efficient method called FastMMD. The core idea of FastMMD is to equivalently transform the MMD with shift-invariant kernels into the a...
متن کاملTwo-Sample Median Test for Vague Data
Classical statistical tests may be sensitive to violations of the fundamental model assumptions inherent in the derivation and construction of these tests. It is obvious that such violations are much more probable in the presence of vague data. Thus nonparametric tests seem to be promising statistical tools. A generalization of the median test for the two-sample problem with vague data is sugge...
متن کاملSupplement to “Ensemble Subsampling for Imbalanced Multivariate Two-Sample Tests”
In this supplemental article, we provide detailed proofs for the propositions and theorems in the main paper. We write the indicator function of the event A as 1A. Let X1, · · · , Xn and Y1, · · · , Yñ be independent random samples in Rd from unknown distributions F and G, respectively, with corresponding densities f and g with respect to Lebesgue measure. The densities are assumed to be contin...
متن کاملEnsemble Subsampling for Imbalanced Multivariate Two-Sample Tests
Some existing nonparametric two-sample tests for equality of multivariate distributions perform unsatisfactorily when the two sample sizes are unbalanced. In particular, the power of these tests tends to diminish with increasingly unbalanced sample sizes. In this article, we propose a new testing procedure to solve this problem. The proposed test, based on the nearest neighbor method by Schilli...
متن کاملA Kernel Two-Sample Test
We propose a framework for analyzing and comparing distributions, which we use to construct statistical tests to determine if two samples are drawn from different distributions. Our test statistic is the largest difference in expectations over functions in the unit ball of a reproducing kernel Hilbert space (RKHS), and is called the maximum mean discrepancy (MMD). We present two distributionfre...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Neural Computation
سال: 2015
ISSN: 0899-7667,1530-888X
DOI: 10.1162/neco_a_00732