Supplementary Material Proofs from Section 2

Neural Information Processing Systems 

The proof of Claim 2.3 is obtained via the following calculation, using the definition of Hermite tensor (Definition 2.2). We will use i,j for indexes in [d]. The above is equivalent to Hk(Bx) = B kHk(x). We construct the truncated distribution A as follows. We first sample x A, then we reject x unless x 2 B. Let A be the distribution of the samples we get from this process. Using Markov's inequality and union bound, we have Then it only remains to verify Ex A [Hk(x)] Ex Nm[Hk(x)] 2 for any k < d.