arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.08218cs.LG
收藏

一致凸代理预测维数的统一下界

Unifying Lower Bounds on Prediction Dimension of Consistent Convex Surrogates

CU Boulder(科罗拉多大学博尔德分校)

Jessie Finocchiaro, Rafael Frongillo, Bo Waggoner

摘要:

给定一个预测任务,理解何时可以和不能设计一致的凸代理损失,特别是低维的,是机器学习研究的一个重要和活跃的领域。预测任务可以作为目标损失给出,如在分类和结构化预测中,或者简单地作为数据的(条件)统计,如在风险度量估计中。这两种情况通常涉及设计和分析替代损失的不同技术。我们使用属性启发的工具统一了这些设置,并给出了预测维度的一般下限。我们的下界收紧现有的结果在离散预测的情况下,表明以前的校准为基础的界限,可以在很大程度上通过属性启发恢复。对于连续估计,我们的下界解决了估计风险和不确定性度量的开放问题。

英文摘要:

Given a prediction task, understanding when one can and cannot design a consistent convex surrogate loss, particularly a low-dimensional one, is an important and active area of machine learning research. The prediction task may be given as a target loss, as in classification and structured prediction, or simply as a (conditional) statistic of the data, as in risk measure estimation. These two scenarios typically involve different techniques for designing and analyzing surrogate losses. We unify these settings using tools from property elicitation, and give a general lower bound on prediction dimension. Our lower bound tightens existing results in the case of discrete predictions, showing that previous calibration-based bounds can largely be recovered via property elicitation. For continuous estimation, our lower bound resolves on open problem on estimating measures of risk and uncertainty.

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。

↑