非匹配模型下信息级联脆弱性的突变
Sharp Thresholds of the Information Cascade Fragility Under a Mismatched Model
摘要:
我们分析了一个顺序决策模型,其中决策者(或玩家)根据自己的私人信息以及之前的决策者的行为做出决策。这样的决策过程通常会导致所谓的\emph{information cascade}或\emph{herding}现象。具体来说,当一些参与者放弃自己的私人信息并模仿早期参与者的行为似乎是合理的时,就会产生级联效应。然而,风险在于,如果最初的决定是错误的,那么整个级联将是错误的。尽管如此,信息级联被认为是脆弱的:存在一系列的\emph{revealing}概率$\{p_{\ell}\}_{\ell\geq1}$,这样,如果概率为$p_{\ell}$的玩家$\ell$忽略前一个玩家的决定,只依赖他的私人信息,那么错误的级联就可以避免。以往研究信息级联脆弱性的相关文献总是假设所有参与者都完全知道信息的泄露概率,这在实际中可能是不现实的。因此,在本文中,我们研究了一个不匹配模型,玩家认为,揭示概率是$\{q_\ell\}_{\ell\in\mathbb{N}}$时,他们真的是$\{p_\ell\}_{\ell\in\mathbb{N}}$,并研究这种不匹配的信息级联的效果。我们考虑了对抗性和概率顺序决策模型,并推导出最佳学习率的封闭形式的表达式,在该表达式中,与某个决策者相关的错误概率为零。我们证明了几个新的相变的渐近学习率的行为。
英文摘要:
We analyze a sequential decision making model in which decision makers (or, players) take their decisions based on their own private information as well as the actions of previous decision makers. Such decision making processes often lead to what is known as the \emph{information cascade} or \emph{herding} phenomenon. Specifically, a cascade develops when it seems rational for some players to abandon their own private information and imitate the actions of earlier players. The risk, however, is that if the initial decisions were wrong, then the whole cascade will be wrong. Nonetheless, information cascade are known to be fragile: there exists a sequence of \emph{revealing} probabilities $\{p_{\ell}\}_{\ell\geq1}$, such that if with probability $p_{\ell}$ player $\ell$ ignores the decisions of previous players, and rely on his private information only, then wrong cascades can be avoided. Previous related papers which study the fragility of information cascades always assume that the revealing probabilities are known to all players perfectly, which might be unrealistic in practice. Accordingly, in this paper we study a mismatch model where players believe that the revealing probabilities are $\{q_\ell\}_{\ell\in\mathbb{N}}$ when they truly are $\{p_\ell\}_{\ell\in\mathbb{N}}$, and study the effect of this mismatch on information cascades. We consider both adversarial and probabilistic sequential decision making models, and derive closed-form expressions for the optimal learning rates at which the error probability associated with a certain decision maker goes to zero. We prove several novel phase transitions in the behaviour of the asymptotic learning rate.
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。