arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1711.05037cs.LG
收藏

回归问题的多源适应

Multiple-Source Adaptation for Regression Problems

EECS, UC Berkeley(加州大学伯克利分校电气工程与计算机科学系);Courant Institute, NYU(纽约大学柯朗研究所);Google Research(谷歌研究院)

Judy Hoffman, Mehryar Mohri, Ningshan Zhang

摘要:

我们提出了一个详细的理论分析的问题,多源适应一般的随机情况下,扩展已知的结果,假设一个单一的目标标签功能。我们的研究结果涵盖了一个更现实的情况下,并显示存在一个单一的强大的预测准确的\emph{any}目标混合源分布。此外,我们提出了一个有效的和实用的优化解决方案,以确定在平方损失的重要情况下的鲁棒预测,通过铸造的问题作为一个DC-编程的实例。我们报告的结果与人工任务和情感分析任务的实验。我们发现,我们的算法优于竞争的方法,产生一个单一的强大的模型,表现良好的任何目标混合物分布。

英文摘要:

We present a detailed theoretical analysis of the problem of multiple-source adaptation in the general stochastic scenario, extending known results that assume a single target labeling function. Our results cover a more realistic scenario and show the existence of a single robust predictor accurate for \emph{any} target mixture of the source distributions. Moreover, we present an efficient and practical optimization solution to determine the robust predictor in the important case of squared loss, by casting the problem as an instance of DC-programming. We report the results of experiments with both an artificial task and a sentiment analysis task. We find that our algorithm outperforms competing approaches by producing a single robust model that performs well on any target mixture distribution.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑