A deterministic and computable Bernstein-von Mises theorem

4 Apr 2019  ·  Guillaume P. Dehaene ·

Bernstein-von Mises results (BvM) establish that the Laplace approximation is asymptotically correct in the large-data limit. However, these results are inappropriate for computational purposes since they only hold over most, and not all, datasets and involve hard-to-estimate constants. In this article, I present a new BvM theorem which bounds the Kullback-Leibler (KL) divergence between a fixed log-concave density $f\left(\boldsymbol{\theta}\right)$ and its Laplace approximation. The bound goes to $0$ as the higher-derivatives of $f\left(\boldsymbol{\theta}\right)$ tend to $0$ and $f\left(\boldsymbol{\theta}\right)$ becomes increasingly Gaussian. The classical BvM theorem in the IID large-data asymptote is recovered as a corollary. Critically, this theorem further suggests a number of computable approximations of the KL divergence with the most promising being: \[ KL\left(g_{LAP},f\right)\approx\frac{1}{2}\text{Var}_{\boldsymbol{\theta}\sim g\left(\boldsymbol{\theta}\right)}\left(\log\left[f\left(\boldsymbol{\theta}\right)\right]-\log\left[g_{LAP}\left(\boldsymbol{\theta}\right)\right]\right) \] An empirical investigation of these bounds in the logistic classification model reveals that these approximations are great surrogates for the KL divergence. This result, and future results of a similar nature, could provide a path towards rigorously controlling the error due to the Laplace approximation and more modern approximation methods.

PDF Abstract
No code implementations yet. Submit your code now

Tasks


Datasets


  Add Datasets introduced or used in this paper

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods


No methods listed for this paper. Add relevant methods here