Order Matters: Improving Domain Adaptation by Reordering Data

ICLR 2026 Conference Submission14413 Authors

Keywords: stochastic variance reduction, unsupervised domain adaptation, maximum mean discrepancy, correlation alignment

TL;DR: A novel stochastic variance reduction technique for unsupervised domain adaptation based on optimising the training data sampling order

Abstract: Domain shift remains a key challenge in deploying machine learning models to the real world. Unsupervised domain adaptation (UDA) aims to address this by minimising domain discrepancy during training, but the discrepancy estimates suffer from high variance in stochastic settings, which can stifle the theoretical benefits of the method. This paper proposes Optimal Reordering of Data for Error-Reduced Estimation of Discrepancy (ORDERED), a novel unbiased stochastic variance reduction technique which reduces the discrepancy estimation error by optimising the order in which the training data are sampled. We consider two specific domain discrepancy losses (correlation alignment and the maximum mean discrepancy), formulate their stochastic estimation error as a function of the data sampling order, and propose a practical optimisation algorithm. Our simulations demonstrate reduced variance compared to related methods, and experiments on a domain shift image classification benchmark show improved target domain accuracy.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Submission Number: 14413