Manifold regularization and semi-supervised learning: some theoretical analyses

@article{Niyogi2013ManifoldRA,
  title={Manifold regularization and semi-supervised learning: some theoretical analyses},
  author={Partha Niyogi},
  journal={Journal of Machine Learning Research},
  year={2013},
  volume={14},
  pages={1229-1250}
}
  • Partha Niyogi
  • Published 2013 in Journal of Machine Learning Research
Manifold regularization (Belkin et al., 2006) is a geometri cally motivated framework for machine learning within which several semi-supervised algorithms have been constructed. Here we try to provide some theoretical understanding of this approach. O ur main result is to expose the natural structure of a class of problems on which manifold regulariz ation methods are helpful. We show that for such problems, no supervised learner can learn effe ctively. On the other hand, a manifold based… CONTINUE READING
Highly Cited
This paper has 54 citations. REVIEW CITATIONS

2 Figures & Tables

Topics

Statistics

05101520112012201320142015201620172018
Citations per Year

54 Citations

Semantic Scholar estimates that this publication has 54 citations based on the available data.

See our FAQ for additional information.