A deterministic and computable Bernstein-von Mises theorem

v1v2 (latest)

A deterministic and computable Bernstein-von Mises theorem

4 April 2019

Guillaume P. Dehaene

ArXiv (abs)PDF HTML

Papers citing "A deterministic and computable Bernstein-von Mises theorem"

5 / 5 papers shown

Title
On the Approximation Accuracy of Gaussian Variational Inference A. Katsevich Philippe Rigollet 87 17 0 05 Jan 2023
How good is your Laplace approximation of the Bayesian posterior? Finite-sample computable error bounds for a variety of useful divergences Mikolaj Kasprzak Ryan Giordano Tamara Broderick 66 4 0 29 Sep 2022
A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness J. Liu Shreyas Padhy Jie Jessie Ren Zi Lin Yeming Wen Ghassen Jerfel Zachary Nado Jasper Snoek Dustin Tran Balaji Lakshminarayanan UQCV BDL 231 51 0 01 May 2022
Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations Alexander Immer Tycho F. A. van der Ouderaa Gunnar Rätsch Vincent Fortuin Mark van der Wilk BDL 147 48 0 22 Feb 2022
Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness Jeremiah Zhe Liu Zi Lin Shreyas Padhy Dustin Tran Tania Bedrax-Weiss Balaji Lakshminarayanan UQCV BDL 290 452 0 17 Jun 2020