University of Cambridge > Talks.cam > Information Theory Seminar > How the strength of the inductive bias affects the generalization performance of interpolators

How the strength of the inductive bias affects the generalization performance of interpolators

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

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

Interpolating models have recently gained popularity in the statistical learning community due to common practices in modern machine learning: complex models achieve good generalization performance despite interpolating high-dimensional training data. In this talk, we prove generalization bounds for high-dimensional linear models that interpolate noisy data generated by a sparse ground truth. In particular, we first show that minimum-l1-norm interpolators achieve high-dimensional asymptotic consistency at a logarithmic rate. Further, as opposed to the regularized or noiseless case, for min-lp-norm interpolators with 1

This talk is part of the Information Theory Seminar series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2023 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity