6 papers
A Computable Measure of Suboptimality for Entropy-Regularised Variational Objectives
Clémentine Chazal, Heishiro Kanagawa, Zheyang Shen +2
Several methods in statistics and machine learning target a probability distribution for which an entropy-regularised variational objective is minimised. This increased flexibility…
Detecting Model Misspecification in Bayesian Inverse Problems via Variational Gradient Descent
Qingyang Liu, Matthew A. Fisher, Zheyang Shen +4
Bayesian inference is optimal when the statistical model is well-specified, while outside this setting Bayesian inference can catastrophically fail; accordingly a wealth of post-Ba…
Predictively-Oriented Kalman Filtering
Zheyang Shen, Gerardo Duran-Martin, Chris. J. Oates
This paper presents a post-Bayesian approach to online filtering in nonlinear state-space models, capable of avoiding over-confident inferences in settings where either the dynamic…
Extrapolation of Tempered Posteriors
Mengxin Xi, Zheyang Shen, Marina Riabiz +2
Tempering is a popular tool in Bayesian computation, being used to transform a posterior distribution into a reference distribution that is more easily approximated. Se…
Operator-Informed Score Matching for Markov Diffusion Models
Zheyang Shen, Huihui Wang, Marina Riabiz +1
Diffusion models are typically trained using score matching, a learning objective agnostic to the underlying noising process that guides the model. This paper argues that Markov no…
Prediction-Centric Uncertainty Quantification via MMD
Zheyang Shen, Jeremias Knoblauch, Sam Power +1
Deterministic mathematical models, such as those specified via differential equations, are a powerful tool to communicate scientific insight. However, such models are necessarily s…