In this paper, we are particularly interested in understanding whether, and how, the choice of distributional robustness bears statistical implications in learning the desired policy, by studying the sample complexity in the widely-used generative model (Kearns and Singh, 1999).

The proof of this lemma requires Lemma A.1, which characterizes the distribution of the residual By Pinsker's inequality, this implies d By Lemma A.1, we have E[ X ( null w w The proof is inspired by Theorem 11.2 in [20], with modifications to our setting. First, we construct a "ghost" dataset The most challenging aspect of the ReLU setting is that we do not have an expression for the TV suffered by the MLE, such as Lemma 4.2 in the linear case. The proof of this Lemma, as well as other Lemmas in this section, can be found in Appendix B.1. Using Lemma B.2 and Lemma B.3, we can form a uniform bound, such that all A straight forward combination of Lemma 4.3 and Lemma B.4 gives the following Theorem. Now we can apply Bernstein's inequality (Theorem 2.10 of [8]).

Neural Information Processing Systems http://nips.cc/

Two-sample testing, where we aim to determine whether two distributions are equal or not equal based on samples from each one, is challenging if we cannot place assumptions on the properties of the two distributions. In particular, certifying equality of distributions, or even providing a tight upper bound on the total variation (TV) distance between the distributions, is impossible to achieve in a distribution-free regime. In this work, we examine the blurred TV distance, a relaxation of TV distance that enables us to perform inference without assumptions on the distributions. We provide theoretical guarantees for distribution-free upper and lower bounds on the blurred TV distance, and examine its properties in high dimensions.