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 2106.03176cs.GTecon.TH
收藏

多任务对等预测的局限性

The Limits of Multi-task Peer Prediction

Shuran Zheng, Fang-Yi Yu, Yiling Chen

摘要:

多任务对等预测的最新进展极大地扩展了我们对多任务对等预测机制的了解。在不同的背景下提出了各种机制,以获取不同类型的信息。但是,我们仍然缺乏了解,当理想的机制将存在一个多任务的同伴预测问题。在这项工作中,我们研究了多任务的同伴预测问题的可启发性。我们考虑一个设计师,他对底层信息结构有一定的了解,并希望从一组参与者中获得某些信息。我们的目标是推断的可能性,有一个理想的机制的基础上的原语的问题。我们的贡献是双重的。首先,我们提供了一个特征的引出多任务同行预测问题,假设设计师只使用评分机制。评分机制是分别奖励参与者对不同任务的报告的机制。表征使用基于单任务设置中功率图表征的几何方法([Lambert和Shoham,2009,Frongillo和Witkowski,2017])。对于一般的机制,我们也给出了一个必要条件的多任务问题是elicitable。其次,我们考虑的情况下,设计师的目的是引起一些属性是线性的参与者的后世界的状态。我们首先表明,在某些情况下,设计师基本上只能引起后方本身。然后,我们研究的情况下,设计师的目的是引起参与者的后验。我们给出了后验可导出的一个必要条件。这个条件意味着,Kong和Schoenebeck提出的机制已经是我们在它们的环境中所能期望的最好的,从这个意义上说,它们的机制可以解决任何可能引发的问题实例。

英文摘要:

Recent advances in multi-task peer prediction have greatly expanded our knowledge about the power of multi-task peer prediction mechanisms. Various mechanisms have been proposed in different settings to elicit different types of information. But we still lack understanding about when desirable mechanisms will exist for a multi-task peer prediction problem. In this work, we study the elicitability of multi-task peer prediction problems. We consider a designer who has certain knowledge about the underlying information structure and wants to elicit certain information from a group of participants. Our goal is to infer the possibility of having a desirable mechanism based on the primitives of the problem. Our contribution is twofold. First, we provide a characterization of the elicitable multi-task peer prediction problems, assuming that the designer only uses scoring mechanisms. Scoring mechanisms are the mechanisms that reward participants' reports for different tasks separately. The characterization uses a geometric approach based on the power diagram characterization in the single-task setting ([Lambert and Shoham, 2009, Frongillo and Witkowski, 2017]). For general mechanisms, we also give a necessary condition for a multi-task problem to be elicitable. Second, we consider the case when the designer aims to elicit some properties that are linear in the participant's posterior about the state of the world. We first show that in some cases, the designer basically can only elicit the posterior itself. We then look into the case when the designer aims to elicit the participants' posteriors. We give a necessary condition for the posterior to be elicitable. This condition implies that the mechanisms proposed by Kong and Schoenebeck are already the best we can hope for in their setting, in the sense that their mechanisms can solve any problem instance that can possibly be elicitable.

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。

↑