具有$\alpha$-散度成本的信息获取
Information Acquisition with $α$-Divergence Costs
AI总结:
本文基于$f$-信息模型,引入以$\alpha$-散度为成本的信息获取模型,刻画最优信息获取,并证明最优选择概率属于$q$-指数族,且参数$\alpha$决定收益水平如何影响各状态下被正概率选择的行动集。
摘要:
基于Bloedel等人(2025)的$f$-信息模型,本文引入一个单参数族的信息获取模型,并刻画了最优信息获取。该族扩展了互信息模型(Matějka和McKay,2015),同时保持了其解析可处理性。信息成本源自$\alpha$-散度,它包含了KL散度($\alpha=-1$)、逆KL散度($\alpha=1$)和平方Hellinger距离($\alpha=0$),并通过Amari(2007)的$\alpha$-积分以闭式表示。最优选择概率属于$q$-指数族,该族出现在非广延统计力学(Tsallis,1988)和交通路径选择的$q$-logit模型(Nakayama,2013)中。在互信息情形(Matějka和McKay,2015)下,该族退化为修正logit。我们还证明了$\alpha$决定了收益水平如何影响各状态下被正概率选择的行动集。
英文摘要:
Building on the $f$-information model of Bloedel et al. (2025), this paper introduces a one-parameter family of information acquisition models and characterizes optimal information acquisition. This family extends the mutual information model (Matějka and McKay, 2015) while preserving its analytical tractability. The information cost is derived from the $α$-divergence, which nests the KL-divergence ($α=-1$), the reverse KL-divergence ($α=1$), and the squared Hellinger distance ($α=0$), and is represented in closed form via the $α$-integration of Amari (2007). The optimal choice probabilities belong to the $q$-exponential family, which appears in nonextensive statistical mechanics (Tsallis, 1988) and in the $q$-logit model of traffic route choice (Nakayama, 2013). This family reduces to the modified logit in the mutual information case (Matějka and McKay, 2015). We further show that the relationship between payoffs and the set of actions chosen with positive probability in each state changes qualitatively across ranges of $α$.
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。