arXiv:1511.03719cs.LG
Universum Prescription: Regularization using Unlabeled Data
Early discovery. Linked by one identifiable commenter. This paper is outside the main ranking; a mention is not an endorsement.
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.
X. Zhang and Y. LeCun had an article [1] about using this technique for regularization very recently. We aren't talking specifically about overfitting in this case, but rather a lack of diversity / size in the training data, however it seems like this kind of thing might help…
kastnerkyleView on HNParent context