发表机构
University of Southampton（南安普顿大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究流数据域适应的随机方差缩减问题，提出在线SVR算法ARROW，通过维护移动平均参考和自适应重新加权小批量数据，使小批量与参考统计量对齐，实验表明该算法在运行时间、方差缩减及目标域准确性方面与离线算法相当。
AI 中文摘要
本文研究了最大均值差异（MMD）和相关对齐（CORAL）损失函数的随机方差缩减（SVR）问题。尽管已提出多种针对这些损失的离线SVR算法，但它们与在线、分布式或增量学习设置不兼容。本文提出了通过在线重新加权的自适应方差缩减（ARROW），这是首个用于流数据的MMD和CORAL在线SVR算法。该方法维护对齐统计量的移动平均参考，并自适应地重新加权输入的小批量数据，以使小批量和参考统计量对齐。此外，还提出了一种宽松的重新加权方案，以使后续的权重优化问题易于处理。在实验和模拟中，ARROW在运行时间、方差缩减程度和目标域准确性方面与离线算法具有竞争力。
英文摘要
This paper studies the problem of stochastic variance reduction (SVR) for the maximum mean discrepancy (MMD) and correlation alignment (CORAL) loss functions. Although various offline SVR algorithms for these losses have been proposed, these are incompatible with online, distributed, or incremental learning settings. This paper presents Adaptive vaRiance Reduction via Online reWeighting (ARROW), the first online SVR algorithm for the MMD and CORAL for streamed data. The method maintains moving average references of the alignment statistics, and adaptively reweights incoming minibatches so that the minibatch and reference statistics are aligned. Further, we propose a relaxed reweighting scheme so that the ensuing weight-optimisation problem is tractable. In experiments and simulations, we show that ARROW performs competitively with offline algorithms in terms of runtime, degree of variance reduction achieved, and target domain accuracy.
