Behavior of Graph Laplacians on Manifolds with Boundary

  title={Behavior of Graph Laplacians on Manifolds with Boundary},
  author={Xueyuan Zhou and Mikhail Belkin},
In manifold learning, algorithms based on graph Laplacians constructed from data have received considerable attention both in practical applications and theoretical analysis. In particular, the convergence of graph Laplacians obtained from sampled data to certain continuous operators has become an active research topic recently. Most of the existi ng work has been done under the assumption that the data is sampled from a manifold without b ndary or that the functions of interests are evaluated… CONTINUE READING


Publications referenced by this paper.
Showing 1-10 of 19 references

Graph Lapl cians and their Convergence on Random Neighborhood Graphs

  • M. Hein, J. yves Audibert, U. V. Luxburg
  • Journal of Machine Learning Research
  • 2007
Highly Influential
4 Excerpts

2004).Diffusion Maps and Geodesic Harmonics

  • S. Lafon
  • 2004
Highly Influential
6 Excerpts

On Learning withIntegral Operators

  • M. Belkin, E. D. Vito
  • Journal of Machine Learning Research
  • 2010

Optimal construction of knearest - neighbor graphs for identifying noisy clusters

  • M. Maier, M. Hein, U. von Luxburg
  • Theoretical Computer Science
  • 2009
2 Excerpts

Semi - Supervised Larning with the Graph Laplacian : The Limit of Infinite Unlabelled Data . Twenty - Third Annual Conference on Neural Information Processing Systems

  • B. Nadler, N. Srebro, X. Zhou
  • 2009
3 Excerpts