Improved dimension dependence in the Bernstein von Mises Theorem via a new Laplace approximation bound

We prove a new simple and explicit bound on the total variation distance between a measure on and its Laplace approximation. The bound is proportional to , which has recently been shown to be the tight rate in terms of dimension dependence. Our bound holds under weak regularity conditions on and at least linear growth of at infinity. We then apply this bound to prove the first ever Bernstein-von Mises (BvM) theorems on the asymptotic normality of posterior distributions in the regime . This improves on the tightest previously known condition, . We establish the BvM for the following data-generating models: 1) exponential families, 2) arbitrary probability mass functions on states, and 3) logistic regression with Gaussian design. Our statements of the BvM are nonasymptotic, taking the form of explicit high-probability bounds. We also show in a general setting that the prior can have a stronger regularizing effect than previously known while still vanishing in the large sample limit.
View on arXiv