提出配对采样方法，降低无监督域适应中的梯度方差，提升模型性能。
Variance-reduced Domain Adaptation using Paired Sampling
- 通过跨域与同域样本配对形成四元组，减少梯度方差
- 在三个域偏移数据集上实现更高目标域准确率
- 适用于需要稳定训练的无监督域适应场景
相关性对齐和最大均值差异是无监督域适应中广泛使用的分布匹配框架。然而，这些损失函数在小批量优化中存在高方差问题，且缺乏有限求和结构，无法兼容经典随机方差缩减（SVR）方法。本文提出针对域适应的配对采样（PSDA），一种专为这类目标设计的新SVR技术。PSDA在域内和域间配对样本，形成始终一起采样的四元组，配对策略旨在最小化期望梯度方差，等价于求解一组线性分配问题。模拟实验表明其方差低于对比方法，三个域偏移数据集上的实验证明了目标域准确率的提升。
原文摘要 · Abstract (English)
Correlation alignment and the maximum mean discrepancy are two widely used distribution-matching frameworks for unsupervised domain adaptation (UDA). However, high variance in these losses has been shown to undermine their effectiveness in minibatch optimisation settings. Furthermore, the losses lack finite-sum structure, which renders them incompatible with classical stochastic variance reduction (SVR) methods. This paper proposes Paired Sampling for Domain Adaptation (PSDA), a novel SVR technique tailored to such objectives. PSDA pairs observations both within and across domains, to form quadruplets that are always sampled together during training. The pairings are designed to minimise expected gradient variance, and reduce to solving a set of linear assignment problems. Our simulations demonstrate reduced variance compared to related methods, and experiments on three domain shift datasets show improved target domain accuracy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。