University of Cambridge > > Machine Learning @ CUED > Unsupervised Risk Estimation with only Structural Assumptions

Unsupervised Risk Estimation with only Structural Assumptions

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

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

Given a model θ and unlabeled samples from a distribution p , we show how to estimate the labeled risk of θ while only making structural (i.e., conditional independence) assumptions about p. This lets us estimate a model’s test error on distributions very different than its training distribution, thus performing unsupervised domain adaptation even without assuming the true predictor remains constant (covariate shift). Furthermore, we can perform discriminative semi-supervised learning, even under model mis-specification. Our technical tool is the method of moments, which allows us to exploit conditional independencies without relying on a specific parametric model. Finally, we introduce a new theoretical framework for grappling with the non-identifiability of the class identities fundamental to unsupervised learning.

This talk is part of the Machine Learning @ CUED series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2024, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity