![]() |
COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. | ![]() |
University of Cambridge > Talks.cam > Isaac Newton Institute Seminar Series > The Bernstein-von Mises theorem for semiparametric mixture
![]() The Bernstein-von Mises theorem for semiparametric mixtureAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact nobody. RCL - Representing, calibrating & leveraging prediction uncertainty from statistics to machine learning Mixture models are a powerful tool for modelling systems with latent variables. Our goal is to estimate some parameter of interest whose distribution depends on some latent variables. Using Bayesian methods, we can find the posterior distribution and get point estimates and uncertainty quantification. However, it is a priori unclear how reliable the Bayesian inference is. With a Bernstein-von Mises theorem we provide a frequentist guarantee for the reliability and asymptotic optimality of the inference. We prove a general BvM theorem and apply it to two specific mixture models: the frailty models and Errors-In-Variables model. This talk is part of the Isaac Newton Institute Seminar Series series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsTrinity Politics Society Isaac Newton Institute Seminar Series Davido 2020Other talksData-driven and Physics-aware Microstructural Modeling of Flowing Complex Fluids OGG Colloquium, title and abstract tba Share your front page Proper Scoring Rules - Estimation and Forecast Evaluation Welcome & Introduction Frequentist guarantees of Bayesian Inference with Missing data |