University of Cambridge > Talks.cam > Statistics > Statistical Risk Characterization of Penalized Likelihood Procedures: An Information-Theoretic Determination

Statistical Risk Characterization of Penalized Likelihood Procedures: An Information-Theoretic Determination

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact .

We review theory for the Minimum Description Length principle, penalized likelihood and its statistical risk. An information theoretic condition on a penalty pen(f) yields the conclusion that the optimizer of the penalized log likelihood criterion log 1/likelihood(f) + pen(f) has risk not more than the index of resolvability, corresponding to the accuracy of the optimizer of the expected value of the criterion. For the linear span of a dictionary of candidate terms, we develop the information theoretic validity of penalties based on the l_1 norm of the coefficients in regression and log-density estimation settings. New results are presented for Gaussian graphical models. This represents joint work with Xi Luo and Sabyasachi Chatterjee.

This talk is part of the Statistics series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2019 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity