|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 listsCCCRR Vascular Biology Research Seminars Cambridge Public Policy Lecture Series Social Enterprise and International Development
Other talksAre Poles at home in the UK? A Public Forum on Immigration Interracial relationships and the 'brown baby' problem: black GIs, white women and their mixed race offspring in World War II Britain Production Processes Group Seminar - "Application of photonics in ultra precision manufacturing" Grammatical case marking: forms and functions Lunchtime Talk: Helen's Bedroom The Romantic Rollercoaster: exploring expectations evoked on hearing a piece of music for the first time using evidence from a prodigious musical savant