Paperlane

no. 13 · Wednesday 11 November 2026

A linear programming approach to finite copula interpolation

Matjaž Omladič, Martin Vuk and Aljaž Zalar

math.ST · 23 pp

Abstract

We consider exact and interval-valued interpolation of multivariate copulas at arbitrary finite configurations in the unit cube. We first characterize when the prescribed data are compatible with a quasi-copula and derive explicit extremal quasi-copula envelopes. The copula interpolation problem is thereby reduced to a copula sandwich problem between these envelopes. Restricting them to the canonical rectangular grid generated by the data coordinates yields a finite linear feasibility system whose elementary-volume constraints are encoded by a cell–vertex incidence matrix. Farkas' lemma then identifies the criterion of Omladič and Stopar with an explicit certificate of infeasibility. Although this criterion is indexed by infinitely many formal cell combinations, we show that it suffices to test finitely many vertices of a sign-polytopal subdivision. We also extend the construction to $k$-increasing discrete quasi-copulas for $2\leq k\leq d$.

comments
23 pages, 0 figures
fields
Statistics Theory
pdf ↗ page arXiv:2611.14008 ↗