Open AccessProceedings Article
Relating Function Class Complexity and Cluster Structure in the Function Domain with Applications to Transduction.
Guy Lever
- 31 Mar 2010
- pp 437-444
TL;DR: This work quantifies the complexity of function classes dened over a graph in terms of the graph structure to facilitate risk analysis relative to cluster structure in the input space which is particularly eective in semi-supervised learning.
read more
Abstract: We relate function class complexity to structure in the function domain. This facilitates risk analysis relative to cluster structure in the input space which is particularly eective in semi-supervised learning. In particular we quantify the complexity of function classes dened over a graph in terms of the graph structure.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Dissertation
Exploiting structure defined by data in machine learning : some new analyses
G. Lever
- 28 Feb 2011
TL;DR: In this paper, a PAC-Bayes prior over a hypothesis class is defined in terms of the unknown true risk and smoothness of hypotheses w.r.t. the unknown data-generating distribution.
References
•Proceedings Article
Semi-supervised learning using Gaussian fields and harmonic functions
Xiaojin Zhu,Zoubin Ghahramani,John Lafferty +2 more
- 21 Aug 2003
TL;DR: An approach to semi-supervised learning is proposed that is based on a Gaussian random field model, and methods to incorporate class priors and the predictions of classifiers obtained by supervised learning are discussed.
Rademacher and gaussian complexities: risk bounds and structural results
Peter L. Bartlett,Shahar Mendelson +1 more
- 01 Mar 2003
TL;DR: In this paper, the authors investigate the use of data-dependent estimates of the complexity of a function class, called Rademacher and Gaussian complexities, in a decision theoretic setting and prove general risk bounds in terms of these complexities.
•Proceedings Article
Semi-Supervised Classification by Low Density Separation
Olivier Chapelle,Alexander Zien +1 more
- 06 Jan 2005
TL;DR: Three semi-supervised algorithms are proposed: deriving graph-based distances that emphazise low density regions between clusters, followed by training a standard SVM, and optimizing the Transductive SVM objective function by gradient descent.
Regularization and Semi-supervised Learning on Large Graphs
Mikhail Belkin,Irina Matveeva,Partha Niyogi +2 more
- 01 Jul 2004
TL;DR: This work considers the problem of labeling a partially labeled graph, which may arise in a number of situations from survey sampling to information retrieval to pattern recognition in manifold settings.
Theory of classification : a survey of some recent advances
TL;DR: The last few years have witnessed important new developments in the theory and practice of pattern classification, see as discussed by the authors for a survey of the main new ideas that have lead to these important recent developments.
Related Papers (5)
Filippo Bonchi,Pawel Sobocinski,Fabio Zanasi +2 more
- 02 Sep 2014
William B. Langdon
- 14 May 1997
William D. Penny,Jérémie Mattout,Nelson J. Trujillo-Barreto +2 more
- 01 Dec 2007