Belief Convergence under Misspecified Learning: A Martingale Approach

Belief Convergence under Misspecified Learning: A Martingale Approach
复制标题

错误指定学习下的信念收敛:马丁格尔方法

DOI:
10.1093/restud/rdac040
复制
发表时间:
2022
期刊:
The Review of Economic Studies
影响因子:
--
通讯作者:
Ishii, Yuhta
Ishii, Yuhta
中科院分区:
--
文献类型:
--
作者:
Frick, Mira;Iijima, Ryota;Ishii, Yuhta

文献摘要

参考文献

被引文献

相似文献

我们提出了一种方法来分析在一大类错误指定的环境中的学习结果,跨越单代理和社会学习。我们在主观模型上引入了一种新的“预测精度”顺序,并观察到这使得部分恢复在正确指定的学习下适用的标准鞅收敛论点是可能的。在此基础上,我们推导出一般条件,以确定给定环境中的信念何时局部或全局收敛到某个长期信念(即,从一些或所有初始信念)。我们证明了这些条件可以应用于:第一,统一和推广了以前所研究的各种收敛结果。其次,它们使我们能够分析学习“缓慢”的环境,例如昂贵的信息获取和循序渐进的社会学习。在这样的环境中,我们说明,即使代理在正确指定的情况下学习到真相,少量的错误指定也会产生极端的学习失败。
We present an approach to analyse learning outcomes in a broad class of misspecified environments, spanning both single-agent and social learning. We introduce a novel “prediction accuracy” order over subjective models and observe that this makes it possible to partially restore standard martingale convergence arguments that apply under correctly specified learning. Based on this, we derive general conditions to determine when beliefs in a given environment converge to some long-run belief either locally or globally (i.e. from some or all initial beliefs). We show that these conditions can be applied, first, to unify and generalize various convergence results in previously studied settings. Second, they enable us to analyse environments where learning is “slow”, such as costly information acquisition and sequential social learning. In such environments, we illustrate that even if agents learn the truth when they are correctly specified, vanishingly small amounts of misspecification can generate extreme failures of learning.
具有私人和共同价值观的社会学习
DOI: 10.1007/s00199-005-0642-5
发表时间: 2006
期刊: Economic Theory
影响因子: 1.3
作者:
J. Goeree;T. Palfrey;Brian W. Rogers
通讯作者: Brian W. Rogers
错误指定学习模型的收敛
DOI: 10.3982/te3558
发表时间: 2021
影响因子: 1.7
作者:
Paul Heidhues;B. Kőszegi;P. Strack
通讯作者: P. Strack
DOI: 10.2139/ssrn.2402889
发表时间: 2013-06
期刊: Microeconomics: Search; Learning; Information Costs & Specific Knowledge; Expectation & Speculation eJournal
影响因子: --
作者:
J. Bohren
通讯作者: J. Bohren
Muto,S:“论 Betrand 竞争中的许可政策”游戏与经济行为。
DOI: --
发表时间: --
期刊:
影响因子: --
作者:
通讯作者: --
DOI: --
发表时间: 2017
期刊: Journal of Economics Theory
影响因子: --
作者:
Wade Hann;Vadim V. Martynov;O. Tamuz
通讯作者: O. Tamuz