|COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring.|
When Bayesians Can't Handle the Truth
If you have a question about this talk, please contact Richard Samworth.
There are elegant results on the consistency of Bayesian updating for well-specified models facing IID or Markovian data, but both completely correct models and fully observed states are vanishingly rare. In this talk, I give conditions for posterior convergence that hold when the prior excludes the truth, which may have complex dependencies. The key dynamical assumption is the convergence of time-averaged log likelihoods (Shannon-McMillan-Breiman property). The main statistical assumption is a building into the prior a form of capacity control related to the method of sieves. With these, I derive posterior and predictive convergence, and a large deviations principle for the posterior, even in infinite-dimensional hypothesis spaces; and clarify role of the prior and of model averaging as regularization devices.
This talk is part of the Statistics series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
Other listsCambridge University Franco-British Student Alliance Medical Genetics Graduate Student Meeting Machine Intelligence Lab Seminar
Other talksIgA-mediated enchained growth mediates protection and modulates bacterial evolution in the intestinal lumen Kellerods and Kelasticas Project Sound A biologically informed hylomorphism The politics of health system metrics, 1924-2000 Change and necessity: forest resilience and conservation for the 21st century