Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2610.40070

Graphical Modeling from Marginal Information via Optimal Transport

Ulysse Naepels·Paul Freulon·Victor M. Panaretos
View original source ↗Read source document ↗Export metadata ↓

Abstract

A graphical model represents multivariate interactions through conditional independence, but requires jointly observed samples to be fitted to data. When individuals cannot be tracked and only marginal observations are available, as with destructive measurements leading to cross-sectional data, the problem of graphical modeling is confounded with that of assembling a joint law. We show how simultaneous graphical modeling and joint law assembly can be realized via a multi-marginal optimal transport problem with graphical cost. Focusing on Gaussian marginals, we generate a joint law satisfying the Markov properties prescribed by a given graph. Within the class of joint distributions respecting the graph and marginals constraints, our construction selects a member by making the interactions set by the graph as strong as possible under a dependence budget measured by relative entropy. In the empirical setting, where only estimates of the marginals are available, we examine the stability of the problem under perturbations of both the marginals and of the graph weights. The resulting error splits into an estimation term, vanishing with the sample size, and a specification term, which quantifies the cost of a misspecified graph. Finally, we illustrate these findings by numerical experiments.

Explore related subjects

stat.MEmath.STstat.TH

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Ulysse Naepels, Paul Freulon, Victor M. Panaretos. 2026-10-29. Graphical Modeling from Marginal Information via Optimal Transport. https://arxiv.org/abs/2610.40070

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

On the closed-loop Volterra method for analyzing and forecasting time series

This paper studies the closed-loop Volterra method for analyzing and predicting stationary time series. The method represents the dependence of a current observation on past observations through polynomial terms, including powers of individual lags and interactions between different lags. Since the number of coefficients increases rapidly with the memory length and polynomial degree, we use the theory of reproducing kernel Hilbert spaces to estimate these coefficients by regularized least squares through kernel evaluations. We establish conditions on marginal moments, temporal dependence, model complexity and regularization under which the prediction risk converges to the minimum mean squared prediction error as the sample size increases. We also consider data-driven selection of tuning parameters by a rolling-origin procedure based on one-step-ahead prediction errors, and show that the resulting selector asymptotically attains the prediction risk of the best candidate in the considered grid. Simulation studies and a real-data application examine the finite-sample performance of the method and its comparison with linear and nonlinear prediction methods.

stat.ME↗
arXiv2026

Boosting e-BH via conditional calibration

The e-BH procedure is an e-value-based multiple testing procedure that provably controls the false discovery rate (FDR) under any dependence structure between the e-values. Despite this appealing theoretical FDR control guarantee, the e-BH procedure often suffers from low power in practice. In this paper, we propose a general framework that boosts the power of e-BH without sacrificing its FDR control under arbitrary dependence. This is achieved by the technique of conditional calibration, where we take as input the e-values and calibrate them to be a set of "boosted e-values" that are guaranteed to be no less -- and are often more -- powerful than the original ones. Our general framework is explicitly instantiated in three classes of multiple testing problems: (1) testing under parametric models, (2) conditional independence testing under the model-X setting, and (3) model-free conformalized selection. Extensive numerical experiments show that our proposed method significantly improves the power of e-BH while continuing to control the FDR. We also demonstrate the effectiveness of our method through an application to an observational study dataset for identifying individuals whose counterfactuals satisfy certain properties.

stat.ME↗
arXiv2026

Differentially Private Covariate Balancing Causal Inference

Differential privacy is the leading mathematical framework for privacy protection, providing a probabilistic guarantee that safeguards individuals' private information when publishing statistics from a dataset. This guarantee is achieved by applying a randomized algorithm to the original data, which introduces unique challenges in data analysis by distorting inherent patterns. In particular, causal inference using observational data while preserving privacy is challenging because it requires a good covariate balance between treatment groups, but checking the covariate balance is challenging when privacy is a primary concern because releasing any statistic (e.g., t-statistic) for the balance check compromises privacy. Additionally, the performance of the privatized estimator critically depends on the choice of differential privacy mechanisms, and it remains unexplored how privacy-protecting causal inference could be conducted with observational data. In this article, we present a differentially private two-stage covariate balancing weighting estimator to infer causal effects from observational data. Our algorithm produces both point and interval estimators with statistical guarantees, such as covariate balance, rate optimality, and oracle budget allocation, under a given privacy budget.

stat.ME↗