University of Cambridge > Talks.cam > Signal Processing and Communications Lab Seminars > Information-theoretic perspectives on learning algorithms

Information-theoretic perspectives on learning algorithms

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

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

In statistical learning theory, generalization error is used to quantify the degree to which a supervised machine learning algorithm may overfit to training data. We overview some recent work [Xu and Raginsky (2017)] that bounds generalization error of empirical risk minimization based on the mutual information between the algorithm input and the algorithm output. We leverage these results to derive generalization error bounds for a broad class of iterative algorithms that are characterized by bounded, noisy updates with Markovian structure, such as stochastic gradient Langevin dynamics (SGLD). We describe certain shortcomings of mutual information-based bounds, and propose alternate bounds that employ the Wasserstein metric from optimal transport theory. We compare the Wasserstein metric-based bounds with the mutual information-based bounds and show that for a class of data generating distributions, the former leads to stronger bounds on the generalization error.

This is joint work with Adrian Tovar-Lopez, Ankit Pensia, and Po-Ling Loh

This talk is part of the Signal Processing and Communications Lab Seminars 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