Statistical Matching via Schrödinger Bridge beyond Conditional Independence

• URL: http://arxiv.org/abs/2606.22770v1
• Date: Mon, 22 Jun 2026 02:19:06 GMT
• Title: Statistical Matching via Schrödinger Bridge beyond Conditional Independence
• Abstract summary: We propose a novel dependency-aware Schrdinger bridge for predictive statistical matching.<n>Our approach couples the two separated databases by tilting the conservative CIA baseline.<n>We demonstrate that our dependency-aware completion consistently improves downstream predictive utility.
• Score: 2.7719338074999538
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Statistical matching combines partially overlapping datasets that share covariates $X$ but observe the target $Y$ and auxiliary variables $Z$ separately. Classical approaches typically invoke the conditional independence assumption (CIA), which makes the problem identifiable but fundamentally implies that the imported auxiliary variable provides no additional predictive power for $Y$ once $X$ is known. To capture this latent $Y$--$Z$ dependence, we propose a novel dependency-aware Schrödinger bridge for predictive statistical matching. Our approach couples the two separated databases by tilting the conservative CIA baseline with a transportation-based compatibility cost, recovering an informative joint distribution. The resulting statistical learning framework yields full probabilistic posterior rules for bidirectional imputation. Theoretically, we establish a sufficient condition under which the learned bridge strictly improves over the CIA baseline, alongside an exact joint recovery guarantee in the Gaussian setting under an appropriate cost. Across synthetic benchmarks and real-world datasets (CelebA and Adult), we demonstrate that our dependency-aware completion consistently improves downstream predictive utility, proving especially beneficial in settings like data recoding where the underlying population exhibits strong $Y$--$Z$ dependence.

Related papers

• A Joint-Distribution Route to Fair Representations with Continuous Sensitive Attributes [12.805268849262243]
  We evaluate independence through a single discrepancy $dleft(P_Z, S, P_Z otimes P_Sright)$ between the joint law and the product of its marginals.<n>We take the Hilbert-Schmidt independence criterion as an instance of the joint discrepancy $d$ to investigate the statistical efficiency of replacing the conditional formulation.
  arXiv  Detail & Related papers  (2026-08-11T04:27:24Z)
• Tight Convergence Rates for Online Distributed Linear Estimation with Adversarial Measurements [66.94250413799232]
  We study mean estimation of a random vector $X$ in a distributed parameter-server-worker setup.<n>Key challenges are adversarial measurements and asynchrony.<n>Results provide a unified finite-time characterization of robustness, identifiability, and statistical efficiency in distributed linear estimation with adversarial workers.
  arXiv  Detail & Related papers  (2026-04-07T11:45:55Z)
• PRISM: Differentially Private Synthetic Data with Structure-Aware Budget Allocation for Prediction [9.016539021471845]
  Differential privacy (DP) provides a mathematical guarantee limiting what an adversary can learn about any individual from released data.<n>Existing DP synthetic data methods treat all features symmetrically, spreading noise uniformly even when the data will serve a specific prediction task.<n>We develop a prediction-centric approach operating in three regimes depending on available structural knowledge.
  arXiv  Detail & Related papers  (2026-02-10T19:17:55Z)
• Dependence-Aware Label Aggregation for LLM-as-a-Judge via Ising Models [55.94503936470247]
  Large-scale AI evaluation increasingly relies on aggregating binary judgments from $K$ annotators, including judges.<n>Most classical methods assume annotators are conditionally independent given the true label $Yin0,1$, an assumption often violated by LLM judges.<n>We study label aggregation through a hierarchy of dependence-aware models based on Ising graphical models and latent factors.
  arXiv  Detail & Related papers  (2026-01-29T21:26:50Z)
• SGD with Dependent Data: Optimal Estimation, Regret, and Inference [3.038061705362137]
  gradient descent (SGD) is shown to accommodate both independent and dependent information under a broad class of stepsize schedules and exploration rate schemes.<n>We show that SGD simultaneously achieves statistically optimal estimation error and regret, extending and improving existing results.<n>For online sparse regression, we develop a new SGD-based algorithm that uses only $d$ units of storage and requires $O(d)$ flops per iteration.
  arXiv  Detail & Related papers  (2026-01-04T04:52:11Z)
• Regression-Based Estimation of Causal Effects in the Presence of Selection Bias and Confounding [52.1068936424622]
  We consider the problem of estimating the expected causal effect $E[Y|do(X)]$ for a target variable $Y$ when treatment $X$ is set by intervention.<n>In settings without selection bias or confounding, $E[Y|do(X)] = E[Y|X]$, which can be estimated using standard regression methods.<n>We propose a framework that incorporates both selection bias and confounding.
  arXiv  Detail & Related papers  (2025-03-26T13:43:37Z)
• Beyond Covariance Matrix: The Statistical Complexity of Private Linear Regression [66.93988594607842]
  Under privacy constraints, the complexity of private linear regression is emphnot captured by the usual covariance matrix.<n>We introduce an Information-Weighted Regression method that attains the optimal rates.<n> Notably, our results demonstrate that joint privacy comes at almost no additional cost.
  arXiv  Detail & Related papers  (2025-02-18T18:35:24Z)
• An Interpretable Measure for Quantifying Predictive Dependence between Continuous Random Variables -- Extended Version [0.0]
  We introduce a novel measure that assesses the degree of association between continuous variables $X$ and $Y$.<n>A key advantage of this measure is its interpretability.<n>We evaluate the performance of our measure on over 90,000 real and synthetic datasets.
  arXiv  Detail & Related papers  (2025-01-18T16:25:20Z)
• Sparse PCA with Oracle Property [115.72363972222622]
  We propose a family of estimators based on the semidefinite relaxation of sparse PCA with novel regularizations. We prove that, another estimator within the family achieves a sharper statistical rate of convergence than the standard semidefinite relaxation of sparse PCA.
  arXiv  Detail & Related papers  (2023-12-28T02:52:54Z)
• A Robustness Analysis of Blind Source Separation [91.3755431537592]
  Blind source separation (BSS) aims to recover an unobserved signal from its mixture $X=f(S)$ under the condition that the transformation $f$ is invertible but unknown. We present a general framework for analysing such violations and quantifying their impact on the blind recovery of $S$ from $X$. We show that a generic BSS-solution in response to general deviations from its defining structural assumptions can be profitably analysed in the form of explicit continuity guarantees.
  arXiv  Detail & Related papers  (2023-03-17T16:30:51Z)
• Outlier-Robust Optimal Transport: Duality, Structure, and Statistical Applications [25.410110072480187]
  Wasserstein distances are sensitive to outliers in the considered distributions. We propose a new outlier-robust Wasserstein distance $mathsfW_pvarepsilon$ which allows for $varepsilon$ outlier mass to be removed from each contaminated distribution.
  arXiv  Detail & Related papers  (2021-11-02T04:05:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.