Sorry, you need to enable JavaScript to visit this website.

Robust importance-weighted cross-validation under sample selection bias

Citation Author(s):
Wouter M Kouw, Jesse H Krijthe, Marco Loog
Submitted by:
Wouter Kouw
Last updated:
11 October 2019 - 4:48pm
Document Type:
Poster
Document Year:
2019
Event:
Presenters:
Wouter Kouw
Paper Code:
27
 

Cross-validation under sample selection bias can, in principle, be done by importance-weighting the empirical risk. However, the importance-weighted risk estimator produces sub-optimal hyperparameter estimates in problem settings where large weights arise with high probability. We study its sampling variance as a function of the training data distribution and introduce a control variate to increase its robustness to problematically large weights.

up
0 users have voted: