A replica analysis of Self-Training of Linear Classifier

arXiv:2205.07739v2 Announce Type: replace-cross
Abstract: Self-training (ST) is a simple and standard approach in semi-supervised learning that has been applied to many machine learning problems. Despite its widespread acceptance and practical effectiveness, it is still not well understood why and how ST improves performance by fitting the model to potentially erroneous pseudo-labels. To investigate the properties of ST, in this study, we derive and analyze a sharp characterization of the behavior of iterative ST when training a linear classifier by …

abstract analysis arxiv classifier cond-mat.dis-nn cond-mat.stat-mech cs.lg labels linear machine machine learning math.st performance practical replica self-training semi-supervised semi-supervised learning simple standard stat.ml stat.th supervised learning training type