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 2605.09565cs.LG
收藏

在线集学习:基于精确度与召回率反馈

Online Set Learning from Precision and Recall Feedback

Stanford University(斯坦福大学);Tel Aviv University and Google Research(特拉维夫大学和谷歌研究);Technion and Google Research(技术学院和谷歌研究);University of Maryland(马里兰大学)

Lee Cohen, Yishay Mansour, Shay Moran, Han Shao

AI总结:

本文研究在线集学习问题,通过精确度和召回率反馈最大化累积奖励。证明有限VC维的假设类可学习,算法结构复杂,挑战传统ERM原则,提供现实和非现实设置下的后悔界。

摘要:

我们考虑在在线设置中学习一个未知域的子集$N_\text{target}$的问题。在每一轮$t$中,学习者预测一组物品$N_t$,并接收两种反馈之一,概率相等:精确度反馈中,从预测集$N_t$中随机选择一个物品并告知其是否属于$N_\text{target}$(若属于则获得奖励),或召回反馈中,从目标集$N_\text{target}$中随机选择一个物品并告知其是否属于$N_t$(若属于则获得奖励)。目标是最大化时间累积奖励。该简单在线集学习问题抽象了多种具有精确度和召回率反馈的学习场景。我们证明,假设类(域的子集族)在该设置下可学习当且仅当其具有有限的Vapnik-Chervonenkis(VC)维,这与经典的PAC特征化相呼应。然而,由此产生的算法结构显著更为复杂:与标准Probably Approximately Correct(PAC)学习不同,其中算法景观由经验风险最小化(ERM)原则简单指导——我们的部分反馈模型可以推翻ERM并甚至所有适当学习规则。我们开发了处理反馈诱导依赖性的算法,获得现实和非现实设置下的后悔界。我们的结果提供了该模型中可学习性的定性特征化,回答了其最基本的问题,同时指出了范围广泛的自然且引人入胜的开放问题,包括确定最优后悔率。

英文摘要:

We consider the problem of learning an unknown subset $N_\text{target}$ of a domain in an online setting. In each round $t$, the learner predicts a set of items ${N}_t$ and receives one of two types of feedback, each with equal probability: precision feedback, in which a randomly chosen item from the predicted set $N_t$ is revealed and the learner is told whether it belongs to $N_\text{target}$ (incurring a reward if it does), or recall feedback, in which a randomly chosen item from the target set $N_\text{target}$ is revealed and the learner is told whether it belongs to $N_t$ (incurring a reward if it does). The goal is to maximize the cumulative reward over time. This simple online set learning problem abstracts a variety of learning scenarios with precision- and recall-type feedback. We show that a hypothesis class (a family of subsets of the domain) is learnable in this setting if and only if it has finite Vapnik-Chervonenkis (VC) dimension, mirroring the classical PAC characterization. However, the resulting algorithmic structure is markedly more intricate: in contrast to standard Probably Approximately Correct (PAC) learning -- where the algorithmic landscape is governed by the simple principle of Empirical Risk Minimization (ERM) -- our partial feedback model can invalidate ERM and even all proper learning rules. We develop algorithms to address the dependencies induced by the feedback, obtaining regret guarantees in both the realizable and agnostic settings. Our results provide a qualitative characterization of learnability in this model, addressing its most basic question, while pointing to a range of natural and intriguing open questions, including the determination of optimal regret rates.

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。

↑