arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.09247cs.LGstat.ML
收藏

审查反馈下学习的泛化误差界

Generalization Error Bounds for Learning under Censored Feedback

The Ohio State University(俄亥俄州立大学);Cisco Research(思科研究院);University of California San Diego(加利福尼亚大学圣迭戈分校)

Yifan Yang, Ali Payani, Parinaz Naghizadeh

AI总结:

本文将DKW不等式扩展到审查反馈导致的非独立同分布数据,给出分类器泛化误差新界,并分析探索技术对误差界的改善,揭示泛化保证与数据收集成本间的权衡。

摘要:

学习理论中的泛化误差界为算法在未见数据上的表现提供了统计保证。在本文中,我们刻画了由审查反馈(又称选择性标注偏差)引起的数据非独立同分布性对此类误差界的影响。审查反馈在许多现实世界的在线选择与分类任务(例如招聘、贷款、推荐系统)中普遍存在:只有当做出有利决策时(例如录用候选人、批准贷款、展示广告),数据点的真实标签才会被揭示,否则标签仍然未知。我们首先将著名的 Dvoretzky-Kiefer-Wolfowitz(DKW)不等式——该不等式刻画了从独立同分布数据中学习得到的经验数据分布 CDF 与理论数据分布 CDF 之间的差距——扩展到因审查反馈而导致数据非独立同分布的问题。随后,我们利用这一 CDF 误差界,为在此类非独立同分布数据上训练的分类器的泛化误差保证提供了一个上界。我们表明,现有的泛化误差界(未考虑审查反馈)无法正确刻画模型的泛化保证,从而验证了提出新误差界的必要性。我们进一步分析了近期文献中提出的(纯探索和有界)探索技术在缓解审查反馈影响、改进我们误差界方面的有效性。综上,我们的发现说明了当未来数据可用性受到审查反馈限制时,决策者应如何在增强算法泛化保证与数据收集成本之间进行权衡。

英文摘要:

Generalization error bounds from learning theory provide statistical guarantees on how well an algorithm will perform on previously unseen data. In this paper, we characterize the impacts of data non-IIDness due to censored feedback (a.k.a. selective labeling bias) on such bounds. Censored feedback is ubiquitous in many real-world online selection and classification tasks (e.g., hiring, lending, recommendation systems) where the true label of a data point is only revealed if a favorable decision is made (e.g., accepting a candidate, approving a loan, displaying an ad), and remains unknown otherwise. We first derive an extension of the well-known Dvoretzky-Kiefer-Wolfowitz (DKW) inequality, which characterizes the gap between empirical and theoretical data distribution CDFs learned from IID data, to problems with non-IID data due to censored feedback. We then use this CDF error bound to provide a bound on the generalization error guarantees of a classifier trained on such non-IID data. We show that existing generalization error bounds (which do not account for censored feedback) fail to correctly capture the model's generalization guarantees, verifying the need for our bounds. We further analyze the effectiveness of (pure and bounded) exploration techniques, proposed by recent literature as a way to alleviate censored feedback, on improving our error bounds. Together, our findings illustrate how a decision maker should account for the trade-off between strengthening the generalization guarantees of an algorithm and the costs incurred in data collection when future data availability is limited by censored feedback.

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。

↑