# Universum Prescription: Regularization using Unlabeled Data

Source: [Universum Prescription: Regularization using Unlabeled Data](<https://www.sota2.com/research/paper/68fa62ed1e209131ce9fbeb5>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T02:48:15.609Z

Authors: Xiang Zhang, Yann LeCun

Published: 2015-11-11T22:46:46.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on CIFAR-100 (test)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test.md>): Image Classification; CIFAR-100 (test); Accuracy: not recorded.

- [Image Classification on CIFAR-10 (test)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test.md>): Image Classification; CIFAR-10 (test); Accuracy: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1511.03719>)

[PDF](<https://arxiv.org/pdf/1511.03719.pdf>)