[Lisa_seminaires] Another UdeM-McGill-MITACS machine learning seminar Thu Dec. 16 at 16h00, MC-103

Dumitru Erhan dumitru.erhan at umontreal.ca
Mer 15 Déc 09:15:02 EST 2010


There's a MITACS seminar at McGill this Thursday, too:

*
Approximate Inference for the Loss-Calibrated Bayesian

*by Simon Lacoste-Julien
Department of Engineering
University of Cambridge

*Location*: McConnell Engineering Bldg (McGill), room* 103*
*Time*: *Thursday, December 16, 16:00 *
*
*
Bayesian decision theory provides a well-defined theoretical framework for
rational decision making under uncertainty. However, even if we assume that
our subjective beliefs about the world have been well-specified, we usually
need to resort to approximations in order to use them in practice. Despite
the central role of the loss in the decision theory formulation, most
prevalent Bayesian approximation methods focus on approximating the
posterior over parameters with no consideration of the loss. In this talk,
our main point is to bring back in focus the need to *calibrate* the
approximation methods to the *loss* under consideration. This philosophy has
already been widely applied in the frequentist statistics / discriminative
machine learning literature, as for example with the use of surrogate
loss functions, but not in Bayesian statistics surprisingly. We
provide examples showing the limitation of disregarding the loss in
standard approximate inference schemes and outline several interesting
research directions arising from this new perspective. As a
first loss-calibrated attempt, we propose an EM-like algorithm on
the Bayesian posterior risk and show how it can improve a standard approach
to Gaussian process classification when the losses are asymmetric.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: https://webmail.iro.umontreal.ca/mailman/private/lisa_seminaires/attachments/20101215/59b302ce/attachment.html 


Plus d'informations sur la liste de diffusion Lisa_seminaires