Beyond Pooling: Matching for Robust Generalization under Data Heterogeneity

• URL: http://arxiv.org/abs/2602.07154v1
• Date: Fri, 06 Feb 2026 19:56:02 GMT
• Title: Beyond Pooling: Matching for Robust Generalization under Data Heterogeneity
• Authors: Ayush Roy, Rudrasis Chakraborty, Lav Varshney, Vishnu Suresh Lokhande,
• Abstract summary: We propose a matching framework that selects samples relative to an adaptive centroid and iteratively refines the representation distribution.<n>We show that these improvements translate to zero-shot medical anomaly detection.
• Score: 9.230247128710865
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Pooling heterogeneous datasets across domains is a common strategy in representation learning, but naive pooling can amplify distributional asymmetries and yield biased estimators, especially in settings where zero-shot generalization is required. We propose a matching framework that selects samples relative to an adaptive centroid and iteratively refines the representation distribution. The double robustness and the propensity score matching for the inclusion of data domains make matching more robust than naive pooling and uniform subsampling by filtering out the confounding domains (the main cause of heterogeneity). Theoretical and empirical analyses show that, unlike naive pooling or uniform subsampling, matching achieves better results under asymmetric meta-distributions, which are also extended to non-Gaussian and multimodal real-world settings. Most importantly, we show that these improvements translate to zero-shot medical anomaly detection, one of the extreme forms of data heterogeneity and asymmetry. The code is available on https://github.com/AyushRoy2001/Beyond-Pooling.

Related papers

• Stratify or Die: Rethinking Data Splits in Image Segmentation [6.391423612294428]
  Iterative Pixel Stratification (IPS) is a label-aware sampling method tailored for segmentation tasks.<n>We present Wasserstein-Driven Evolutionary Stratification (WDES), a novel genetic algorithm designed to minimize the Wasserstein distance.
  arXiv  Detail & Related papers  (2025-09-25T12:04:26Z)
• Wasserstein Convergence of Score-based Generative Models under Semiconvexity and Discontinuous Gradients [3.007949058551534]
  Score-based Generative Models (SGMs) approximate a data distribution by perturbing it with Gaussian noise and subsequently denoising it via a learned diffusion process.<n>We establish the first non-asymotic Wasserstein-2 convergence guarantees for SGMs targeting semi-one order with potentially discontinuous gradients.
  arXiv  Detail & Related papers  (2025-05-06T11:17:15Z)
• Towards Self-Supervised Covariance Estimation in Deep Heteroscedastic Regression [102.24287051757469]
  We study self-supervised covariance estimation in deep heteroscedastic regression.<n>We derive an upper bound on the 2-Wasserstein distance between normal distributions.<n>Experiments over a wide range of synthetic and real datasets demonstrate that the proposed 2-Wasserstein bound coupled with pseudo label annotations results in a computationally cheaper yet accurate deep heteroscedastic regression.
  arXiv  Detail & Related papers  (2025-02-14T22:37:11Z)
• Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers [49.97755400231656]
  We present the first performance guarantee with explicit dimensional dependencies for general score-mismatched diffusion samplers.<n>We show that score mismatches result in an distributional bias between the target and sampling distributions, proportional to the accumulated mismatch between the target and training distributions.<n>This result can be directly applied to zero-shot conditional samplers for any conditional model, irrespective of measurement noise.
  arXiv  Detail & Related papers  (2024-10-17T16:42:12Z)
• Distributionally and Adversarially Robust Logistic Regression via Intersecting Wasserstein Balls [8.720733751119994]
  We study the underlying optimization problem, develop efficient solution algorithms, and demonstrate that the proposed method outperforms benchmark approaches on standard datasets.<n>Inspired by the former, we study the Wasserstein DR counterpart of ARO for logistic regression and show it admits a tractable convex optimization reformulation.
  arXiv  Detail & Related papers  (2024-07-18T15:59:37Z)
• Collaborative Heterogeneous Causal Inference Beyond Meta-analysis [68.4474531911361]
  We propose a collaborative inverse propensity score estimator for causal inference with heterogeneous data. Our method shows significant improvements over the methods based on meta-analysis when heterogeneity increases.
  arXiv  Detail & Related papers  (2024-04-24T09:04:36Z)
• IBADR: an Iterative Bias-Aware Dataset Refinement Framework for Debiasing NLU models [52.03761198830643]
  We propose IBADR, an Iterative Bias-Aware dataset Refinement framework. We first train a shallow model to quantify the bias degree of samples in the pool. Then, we pair each sample with a bias indicator representing its bias degree, and use these extended samples to train a sample generator. In this way, this generator can effectively learn the correspondence relationship between bias indicators and samples.
  arXiv  Detail & Related papers  (2023-11-01T04:50:38Z)
• RGM: A Robust Generalizable Matching Model [49.60975442871967]
  We propose a deep model for sparse and dense matching, termed RGM (Robust Generalist Matching) To narrow the gap between synthetic training samples and real-world scenarios, we build a new, large-scale dataset with sparse correspondence ground truth. We are able to mix up various dense and sparse matching datasets, significantly improving the training diversity.
  arXiv  Detail & Related papers  (2023-10-18T07:30:08Z)
• Data thinning for convolution-closed distributions [2.299914829977005]
  We propose data thinning, an approach for splitting an observation into two or more independent parts that sum to the original observation. We show that data thinning can be used to validate the results of unsupervised learning approaches.
  arXiv  Detail & Related papers  (2023-01-18T02:47:41Z)
• Good Classifiers are Abundant in the Interpolating Regime [64.72044662855612]
  We develop a methodology to compute precisely the full distribution of test errors among interpolating classifiers. We find that test errors tend to concentrate around a small typical value $varepsilon*$, which deviates substantially from the test error of worst-case interpolating model. Our results show that the usual style of analysis in statistical learning theory may not be fine-grained enough to capture the good generalization performance observed in practice.
  arXiv  Detail & Related papers  (2020-06-22T21:12:31Z)
• Robust M-Estimation Based Bayesian Cluster Enumeration for Real Elliptically Symmetric Distributions [5.137336092866906]
  Robustly determining optimal number of clusters in a data set is an essential factor in a wide range of applications. This article generalizes so that it can be used with any arbitrary Really Symmetric (RES) distributed mixture model. We derive a robust criterion for data sets with finite sample size, and also provide an approximation to reduce the computational cost at large sample sizes.
  arXiv  Detail & Related papers  (2020-05-04T11:44:49Z)

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.