Detecting Correlated Gaussian Databases
share
This paper considers the problem of detecting whether two databases, each consisting of n users with d Gaussian features, are correlated. Under the null hypothesis, the databases are independent. Under the alternate hypothesis, the features are correlated across databases, under an unknown row permutation. A simple test is developed to show that detection is achievable above ρ^2 ≈1/d. For the converse, the truncated second moment method is used to establish that detection is impossible below roughly ρ^2 ≈1/d√(n). These results are compared to the corresponding recovery problem, where the goal is to decode the row permutation, and a converse bound of roughly ρ^2 ≈ 1 - n^-4/d has been previously shown. For certain choices of parameters, the detection achievability bound outperforms this recovery converse bound, demonstrating that detection can be easier than recovery in this scenario.
READ FULL TEXT