论文标题
模型错误指定下的非扰动拉普拉斯近似
Nonasymptotic Laplace approximation under model misspecification
论文作者
论文摘要
我们向贝叶斯推论的对数 - 边界的可能性提出了非反应的两侧边界。经典的拉普拉斯近似被恢复为前学期。我们的派生允许模型错误指定，并允许参数维度随样本量增长。我们没有对后部的渐近形状做出任何假设，而是需要以可能比率的某些规律性条件，并且后部需要充分浓缩。
We present non-asymptotic two-sided bounds to the log-marginal likelihood in Bayesian inference. The classical Laplace approximation is recovered as the leading term. Our derivation permits model misspecification and allows the parameter dimension to grow with the sample size. We do not make any assumptions about the asymptotic shape of the posterior, and instead require certain regularity conditions on the likelihood ratio and that the posterior to be sufficiently concentrated.
