Composition and tensor train structure in polynomial optimization
Abstract
We study polynomial optimization problems whose objective has a composition or tensor train structure. These polynomials can be evaluated as a sequence of maps, giving rise to intermediate variables (``states'') of dimension lower than the ambient dimension. Structures like these arise naturally in dynamical systems, Markov chains, and neural networks. We develop two moment-SOS (sums of squares) hierarchies that exploit this composition structure in different ways. The first one, termed state-lifting chordal, is based on the correlative sparsity graph of the problem. The second one, termed state-lifting push-forward, encodes the structure at the level of the measures directly. Numerical experiments demonstrate that the proposed methods can compute certified bounds for problems with hundreds or even a thousand variables. To illustrate the versatility of the hierarchies we apply them to Markov chain optimization, quantum optimal control, and neural networks.
Cite
@article{arxiv.2604.17563,
title = {Composition and tensor train structure in polynomial optimization},
author = {Llorenç Balada Gaggioli and Didier Henrion and Milan Korda},
journal= {arXiv preprint arXiv:2604.17563},
year = {2026}
}