Two-Sided Bounds for Entropic Optimal Transport via a Rate-Distortion Integral
Abstract
We show that the maximum expected inner product between a random vector and the standard normal vector over all couplings subject to a mutual information constraint or regularization is equivalent to a truncated integral involving the rate-distortion function, up to universal multiplicative constants. The proof is based on a lifting technique, which constructs a Gaussian process indexed by a random subset of the type class of the probability distribution involved in the information-theoretic ine...
Description / Details
We show that the maximum expected inner product between a random vector and the standard normal vector over all couplings subject to a mutual information constraint or regularization is equivalent to a truncated integral involving the rate-distortion function, up to universal multiplicative constants. The proof is based on a lifting technique, which constructs a Gaussian process indexed by a random subset of the type class of the probability distribution involved in the information-theoretic inequality, and then applying a form of the majorizing measure theorem.
Source: arXiv:2604.14061v1 - http://arxiv.org/abs/2604.14061v1 PDF: https://arxiv.org/pdf/2604.14061v1 Original Link: http://arxiv.org/abs/2604.14061v1
Please sign in to join the discussion.
No comments yet. Be the first to share your thoughts!
Apr 17, 2026
Data Science
Statistics
0