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 two domain shift image classification benchmarks show improved target domain accuracy.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.05084 [cs.LG] |
| (or arXiv:2605.05084v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.05084 arXiv-issued DOI via DataCite (pending registration) |
From: Andrea Napoli [view email]
[v1]
Wed, 6 May 2026 16:20:24 UTC (184 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。