论文标题
当最佳概率分布不是唯一时，自由能的渐近行为
Asymptotic Behavior of Free Energy When Optimal Probability Distribution Is Not Unique
论文作者
论文摘要
贝叶斯推断是一种广泛使用的统计方法。自由能和概括损失用于估计贝叶斯推断的准确性，在没有独特的最佳参数的单数模型中很小。但是，当有多个最佳概率分布时，它们的特征尚不清楚。在本文中，我们从理论上得出了在最佳概率分布不是唯一的，并表明它们与常规渐近分析的术语不同，因此我们从理论上得出了概括损失和自由能的渐近行为。
Bayesian inference is a widely used statistical method. The free energy and generalization loss, which are used to estimate the accuracy of Bayesian inference, are known to be small in singular models that do not have a unique optimal parameter. However, their characteristics are not yet known when there are multiple optimal probability distributions. In this paper, we theoretically derive the asymptotic behaviors of the generalization loss and free energy in the case that the optimal probability distributions are not unique and show that they contain asymptotically different terms from those of the conventional asymptotic analysis.
