Graph-Informed Adversarial Modeling: Infimal Subadditivity of Interpolative Divergences

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Birmpa, Panagiota, Hall, Eric Joseph
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912997434195968
author Birmpa, Panagiota
Hall, Eric Joseph
author_facet Birmpa, Panagiota
Hall, Eric Joseph
contents We study adversarial learning when the target distribution factorizes according to a known Bayesian network. For interpolative divergences, including $(f,Γ)$-divergences, we prove a new infimal subadditivity principle showing that, under suitable conditions, a global variational discrepancy is controlled by an average of family-level discrepancies aligned with the graph. In an additive regime, the surrogate is exact. This closes a theoretical gap in the literature; existing subadditivity results justify graph-informed adversarial learning for classical discrepancies, but not for interpolative divergences, where the usual factorization argument breaks down. In turn, we provide a justification for replacing a standard, graph-agnostic GAN with a monolithic discriminator by a graph-informed GAN (GiGAN) with localized family-level discriminators, without requiring the optimizer itself to factorize according to the graph. We also obtain parallel results for integral probability metrics and proximal optimal transport divergences, identify natural discriminator classes for which the theory applies, and present experiments showing improved stability and structural recovery relative to graph-agnostic baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2603_20025
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Graph-Informed Adversarial Modeling: Infimal Subadditivity of Interpolative Divergences
Birmpa, Panagiota
Hall, Eric Joseph
Machine Learning
Statistics Theory
62H22 (Primary) 68T07, 49Q22, 62B10 (Secondary)
We study adversarial learning when the target distribution factorizes according to a known Bayesian network. For interpolative divergences, including $(f,Γ)$-divergences, we prove a new infimal subadditivity principle showing that, under suitable conditions, a global variational discrepancy is controlled by an average of family-level discrepancies aligned with the graph. In an additive regime, the surrogate is exact. This closes a theoretical gap in the literature; existing subadditivity results justify graph-informed adversarial learning for classical discrepancies, but not for interpolative divergences, where the usual factorization argument breaks down. In turn, we provide a justification for replacing a standard, graph-agnostic GAN with a monolithic discriminator by a graph-informed GAN (GiGAN) with localized family-level discriminators, without requiring the optimizer itself to factorize according to the graph. We also obtain parallel results for integral probability metrics and proximal optimal transport divergences, identify natural discriminator classes for which the theory applies, and present experiments showing improved stability and structural recovery relative to graph-agnostic baselines.
title Graph-Informed Adversarial Modeling: Infimal Subadditivity of Interpolative Divergences
topic Machine Learning
Statistics Theory
62H22 (Primary) 68T07, 49Q22, 62B10 (Secondary)
url https://arxiv.org/abs/2603.20025