arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 0902.3430cs.LGcs.AI
收藏

领域自适应:学习界与算法

Domain Adaptation: Learning Bounds and Algorithms

Google Research(谷歌研究院);Tel Aviv Univ.(特拉维夫大学);Courant Institute(库朗研究所);New York University(纽约大学)

Yishay Mansour, Mehryar Mohri, Afshin Rostamizadeh

AI总结:

本文提出差异距离以度量分布差异,给出其估计的复杂度界和领域自适应泛化界,并为最小化经验差异设计新算法,实验验证了其在领域自适应中的有效性。

摘要:

本文研究领域自适应的一般问题,该问题出现在各种应用中,其中已标注样本的分布与测试数据的分布存在一定差异。在 Ben-David 等人(2007)先前工作的基础上,我们引入了一种新的分布间距离,即差异距离(discrepancy distance),该距离专为具有任意损失函数的自适应问题而设计。我们给出了针对不同损失函数从有限样本估计差异距离的 Rademacher 复杂度界。利用该距离,我们为一大类损失函数推导了新的领域自适应泛化界。我们还针对一大类基于正则化的算法提出了一系列新的自适应界,包括基于经验差异的支持向量机和核岭回归。这促使我们分析针对各种损失函数最小化经验差异的问题,并为此给出了新的算法。我们报告了初步实验结果,证明了我们的差异最小化算法在领域自适应中的优势。

英文摘要:

This paper addresses the general problem of domain adaptation which arises in a variety of applications where the distribution of the labeled sample available somewhat differs from that of the test data. Building on previous work by Ben-David et al. (2007), we introduce a novel distance between distributions, discrepancy distance, that is tailored to adaptation problems with arbitrary loss functions. We give Rademacher complexity bounds for estimating the discrepancy distance from finite samples for different loss functions. Using this distance, we derive novel generalization bounds for domain adaptation for a wide family of loss functions. We also present a series of novel adaptation bounds for large classes of regularization-based algorithms, including support vector machines and kernel ridge regression based on the empirical discrepancy. This motivates our analysis of the problem of minimizing the empirical discrepancy for various loss functions for which we also give novel algorithms. We report the results of preliminary experiments that demonstrate the benefits of our discrepancy minimization algorithms for domain adaptation.

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。

↑