![]() |
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 > Artificial Intelligence Research Group Talks (Computer Laboratory) > Learning under model misspecification
Learning under model misspecificationAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Mateja Jamnik. Bayesian statistics is one of the most employed tools for uncertainty modelling in deep learning. But, in this talk, we will present recent research which cast doubts about the optimality of the Bayesian approach for this task. More precisely, we will present a novel PAC -Bayesian analysis of Bayesian model averaging showing that it is only optimal for generalization when the model class is perfectly specified, something which rarely happens in practice. By building on this theoretical analysis, we will introduce a novel learning framework based on the minimization of a new family of PAC -Bayesian bounds which explicitly assume that the model class is misspecified (a much more realistic assumption). We will also discuss strong connections with deep ensemble methods. This talk is part of the Artificial Intelligence Research Group Talks (Computer Laboratory) series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsCambridge Review of International Affairs Museum of Zoology weedmp3Other talksProbing reionization with the Lyman-alpha forest and the CMB Space projected electrical conductivity and spectral properties of the conduction matrix Cadence Design Systems: Intelligent System Design and Computational Software TBC Further explorations in Peru Joern Coers (Duke University) and Eva Frickel (The Francis Crick Institute) |