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 1801.02042econ.THcs.GTcs.SI
收藏

从邻居那里学习一个不断变化的国家

Learning from Neighbors about a Changing State

Krishna Dasaratha, Benjamin Golub, Nir Hak

摘要:

智能体使用私有信号和邻居过去对状态的估计来了解变化的状态。我们提出了一个模型,在平衡贝叶斯代理使用邻居的估计,简单地采取加权和时不变的权重。因此,这种动态与网络中易于处理的DeGroot学习模型相似,但它是作为一种均衡结果而不是行为假设出现的。我们研究信息聚合是否是接近最优的邻域变大。其中一个关键条件是信号多样性:每个个体的邻居都有私人信号,这些信号不仅包含独立的信息,而且具有足够不同的分布。没有信号分集$\unicode{x2013}$,如果专用信号是I.I.D. $\unicode{x2013}$学习在所有网络中都是次优的,在某些网络中效率非常低。转向社会影响,我们发现它是一个更敏感的信号质量比一个人的邻居的数量,与标准模型与外源更新规则。

英文摘要:

Agents learn about a changing state using private signals and their neighbors' past estimates of the state. We present a model in which Bayesian agents in equilibrium use neighbors' estimates simply by taking weighted sums with time-invariant weights. The dynamics thus parallel those of the tractable DeGroot model of learning in networks, but arise as an equilibrium outcome rather than a behavioral assumption. We examine whether information aggregation is nearly optimal as neighborhoods grow large. A key condition for this is signal diversity: each individual's neighbors have private signals that not only contain independent information, but also have sufficiently different distributions. Without signal diversity $\unicode{x2013}$ e.g., if private signals are i.i.d. $\unicode{x2013}$ learning is suboptimal in all networks and highly inefficient in some. Turning to social influence, we find it is much more sensitive to one's signal quality than to one's number of neighbors, in contrast to standard models with exogenous updating rules.

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。

↑