The Sample Complexity of Semi-Supervised Learning with Nonparametric Mixture Models

Chen DanLiu LeqiBryon AragamPradeep K. RavikumarEric P. Xing

We study the sample complexity of semi-supervised learning (SSL) and introduce new assumptions based on the mismatch between a mixture model learned from unlabeled data and the true mixture model induced by the (unknown) class conditional distributions. Under these assumptions, we establish an $\Omega(K\log K)$ labeled sample complexity bound without imposing parametric assumptions, where $K$ is the number of classes... (read more)

PDF Abstract

No code implementations yet. Submit your code now