Estimating Certain Integral Probability Metric (IPM) is as Hard as Estimating under the IPM

11/02/2019
by   Tengyuan Liang, et al.
0

We study the minimax optimal rates for estimating a range of Integral Probability Metrics (IPMs) between two unknown probability measures, based on n independent samples from them. Curiously, we show that estimating the IPM itself between probability measures, is not significantly easier than estimating the probability measures under the IPM. We prove that the minimax optimal rates for these two problems are multiplicatively equivalent, up to a loglog (n)/log (n) factor.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset