SemiSupervised Learning: the Case When Unlabeled Data is Equally Useful
Abstract
Semisupervised learning algorithms attempt to take advantage of relatively inexpensive unlabeled data to improve learning performance. In this work, we consider statistical models where the data distributions can be characterized by continuous parameters. We show that under certain conditions on the distribution, unlabeled data is equally useful as labeled date in terms of learning rate. Specifically, let $n, m$ be the number of labeled and unlabeled data, respectively. It is shown that the learning rate of semisupervised learning scales as $O(1/n)$ if $m\sim n$, and scales as $O(1/n^{1+\gamma})$ if $m\sim n^{1+\gamma}$ for some $\gamma>0$, whereas the learning rate of supervised learning scales as $O(1/n)$.
 Publication:

arXiv eprints
 Pub Date:
 May 2020
 DOI:
 10.48550/arXiv.2005.11018
 arXiv:
 arXiv:2005.11018
 Bibcode:
 2020arXiv200511018Z
 Keywords:

 Computer Science  Machine Learning;
 Computer Science  Information Theory;
 Statistics  Machine Learning
 EPrint:
 Published in UAI 2020. This version: an error in Lemma 2 is corrected