Robust Semi-supervised Learning via $f$-Divergence and $\alpha$-R\'enyi Divergence

arXiv:2405.00454v1 Announce Type: new
Abstract: This paper investigates a range of empirical risk functions and regularization methods suitable for self-training methods in semi-supervised learning. These approaches draw inspiration from various divergence measures, such as $f$-divergences and $\alpha$-R\'enyi divergences. Inspired by the theoretical foundations rooted in divergences, i.e., $f$-divergences and $\alpha$-R\'enyi divergence, we also provide valuable insights to enhance the understanding of our empirical risk functions and regularization techniques. In the pseudo-labeling and entropy minimization techniques as self-training methods for effective …

abstract alpha arxiv cs.it cs.lg divergence functions inspiration math.it paper regularization risk robust self-training semi-supervised semi-supervised learning stat.ml supervised learning training type via