Sparse approximation of triangular transports. Part I: the finite dimensional case
Abstract
For two probability measures and with analytic densities on the -dimensional cube , we investigate the approximation of the unique triangular monotone Knothe-Rosenblatt transport , such that the pushforward equals . It is shown that for there exist approximations of , based on either sparse polynomial expansions or deep ReLU neural networks, such that the distance between and decreases exponentially. More precisely, we prove error bounds of the type (or for neural networks), where refers to the dimension of the ansatz space (or the size of the network) containing ; the notion of distance comprises the Hellinger distance, the total variation distance, the Wasserstein distance and the Kullback-Leibler divergence. Our construction guarantees to be a monotone triangular bijective transport on the hypercube . Analogous results hold for the inverse transport . The proofs are constructive, and we give an explicit a priori description of the ansatz space, which can be used for numerical implementations.
Keywords
Cite
@article{arxiv.2006.06994,
title = {Sparse approximation of triangular transports. Part I: the finite dimensional case},
author = {Jakob Zech and Youssef Marzouk},
journal= {arXiv preprint arXiv:2006.06994},
year = {2021}
}
Comments
The original manuscript arXiv:2006.06994v1 has been split into two parts; the present paper is the first part