University of Cambridge > Talks.cam > MRC Biostatistics Unit Seminars > “Squeezing the most out of ridge”

“Squeezing the most out of ridge”

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

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

Ridge regression is nowadays regarded as a somewhat old-fashioned technique: most statisticians prefer sparse models, while machine learners use non-linear, multi-layer prediction algorithms. The aim of this talk is to endorse ridge by illustrating its strengths, from a methodological, computational and applied perspective, including:

Flexibility (in terms of output and type of covariates)

Bayesian counterpart facilitates empirical Bayes estimation of penalty parameter(s)

Differential penalization for multi-modal (e.g. multi-omics) data

Penalty weights moderated by (external) information on the features:

Co-data

Effective posterior feature selection

Computational efficiency

Performance in clinical (omics) prediction problems

These strengths will be illustrated on a cancer multi-omics prediction problem.

This talk is part of the MRC Biostatistics Unit Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2020 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity