arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2202.03045cs.LGstat.ML
收藏

度量值回归

Metric-valued regression

Dan Tsir Cohen, Aryeh Kontorovich

AI总结:

本文提出了一种在两个度量空间间学习映射的高效算法,基于度量中位数,解决了无界损失情况下非理想设定下的可学习性问题。

摘要:

我们提出了一种在两个度量空间 $\X$ 和 $\Y$ 之间学习映射的高效算法。我们的方法在 $\X$ 和 $\Y$ 拓扑可分且 $\Y$ 在期望意义下“有界”时具有强贝叶斯一致性(我们的术语;可分性假设可以适度放宽)。在这一一般性水平上,我们的结果是首个在无界损失情况下,在非理想设定下可学习的结论。我们的技术基于度量中位数(弗雷歇均值的一种变体),与现有方法形成显著区别,我们证明现有方法在一般实例空间和标签空间度量上无法实现贝叶斯一致性。我们的证明引入了 {\em 半稳定压缩} 技术,这可能具有独立兴趣。

英文摘要:

We propose an efficient algorithm for learning mappings between two metric spaces, $\X$ and $\Y$. Our procedure is strongly Bayes-consistent whenever $\X$ and $\Y$ are topologically separable and $\Y$ is "bounded in expectation" (our term; the separability assumption can be somewhat weakened). At this level of generality, ours is the first such learnability result for unbounded loss in the agnostic setting. Our technique is based on metric medoids (a variant of Fréchet means) and presents a significant departure from existing methods, which, as we demonstrate, fail to achieve Bayes-consistency on general instance- and label-space metrics. Our proofs introduce the technique of {\em semi-stable compression}, which may be of independent interest.

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。

↑