We describe and analyze efficient algorithms for learning a linear predictor from examples when the learner can only view a few attributes of each training example. This is the case, for instance, in medical research, where each patient participating in the experiment is only willing to go through a small number of tests. Our analysis bounds the number of additional examples sufficient to compen-sate for the lack of full information on each training example. We demonstrate the efficiency of our algorithms by showing that when running on digit recognition data, they obtain a high prediction accuracy even when the learner gets to see only four pixels of each image. Copyright 2010 by the author(s)/owner(s).
Efficient learning with partially observed attributes / N. Cesa-Bianchi, S. Shalev-Shwartz, O. Shamir - In: Proceedings of the 27th International Conference on Machine LearningMadison : Omnipress, 2010. - ISBN 9781605589077. - pp. 183-190 (( Intervento presentato al 27. convegno International Conference on Machine Learning tenutosi a Haifa, Israel nel 2010.
Efficient learning with partially observed attributes
N. Cesa-BianchiPrimo
;
2010
Abstract
We describe and analyze efficient algorithms for learning a linear predictor from examples when the learner can only view a few attributes of each training example. This is the case, for instance, in medical research, where each patient participating in the experiment is only willing to go through a small number of tests. Our analysis bounds the number of additional examples sufficient to compen-sate for the lack of full information on each training example. We demonstrate the efficiency of our algorithms by showing that when running on digit recognition data, they obtain a high prediction accuracy even when the learner gets to see only four pixels of each image. Copyright 2010 by the author(s)/owner(s).Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.