Universum Prescription: Regularization using Unlabeled Data
release_pgpfxd4qv5hjpbytsitlms4okm
by
Xiang Zhang, Yann LeCun
2015
Abstract
This paper shows that simply prescribing "none of the above" labels to
unlabeled data has a beneficial regularization effect to supervised learning.
We call it universum prescription by the fact that the prescribed labels cannot
be one of the supervised labels. In spite of its simplicity, universum
prescription obtained competitive results in training deep convolutional
networks for CIFAR-10, CIFAR-100, STL-10 and ImageNet datasets. A qualitative
justification of these approaches using Rademacher complexity is presented. The
effect of a regularization parameter -- probability of sampling from unlabeled
data -- is also studied empirically.
In text/plain
format
Archived Files and Locations
application/pdf 544.7 kB
file_yqserqzil5evbdhx4furb7butq
|
arxiv.org (repository) web.archive.org (webarchive) |
1511.03719v1
access all versions, variants, and formats of this works (eg, pre-prints)