A1624
Title: Generative modeling via hierarchical tensor sketching
Authors: Yifan Peng - University of Chicago (United States) [presenting]
yian chen - University of Chicago (United States)
Miles Stoudenmire - Flatiron Institute (United States)
Yuehaw Khoo - University of Chicago (United States)
Abstract: A hierarchical tensor-network approach is proposed for approximating high-dimensional probability density via empirical distribution. This leverages randomized singular value decomposition (SVD) techniques and involves solving linear equations for tensor cores in this tensor network. The complexity of the resulting algorithm scales linearly in the dimension of the high-dimensional density. An analysis of estimation error demonstrates the effectiveness of this method through several numerical experiments.
