Abstract
This paper establishes the geometric framework of manifold learning. After summarizing the requirements of the classical manifold learning methods, we construct the smooth homeomorphism between the manifold and its tangent space. Then we propose a new algorithm via homeomorphic tangent space (LHTS). We also present another algorithm via compactness (CSLI) by analyzing the topological properties of manifolds. We illustrate our algorithm on the completed manifold and non-completed manifold. We also address several theoretical issues for further research and improvements.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Theodoridis, S.: Konstantinos Koutroumbas: Pattern Recognition, 4th edn. Machinery Industry Press, Beijing (2009)
Zhou, Z.: Machine Learning, pp. 53–63, 97–113, 171–173. Tsinghua University Press, Beijing (2016)
Tenenbaum, J.B., De Silva, V.: A globel geometric framework for nonlinear dimensionality reduction. Science 290(5500), 2319–2323 (2000)
Roweis, S., Saul, L.: Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500), 2323–2326 (2000)
Zhang, Z., Zha, H.: Principal manifolds and nonlinear dimensionality reduction via tangent space alignment. SIAM J. Sci. Comput. 26(1), 313–338 (2004)
Chen, W.: Introduction to Differential Geometry, pp. 37–94. Higher Education Press, Beijing (2013)
John, M.L.: Introduction to Smooth Manifolds, pp. 2–122. Springer, Heidelberg (2012)
Peter, D.L.: Functional Analysis, pp. 43–51, 233–244. Higher Education Press, Beijing (2007)
Jiang, Z., Sun, S.: Functional Analysis, pp. 19–25. Higher Education Press, Beijing (2005)
Munkres, J.R.: Topology, 2nd edn, pp. 75–118, 148–186, 200–227, 322–340. Prentice Hall, Upper Saddle River (2000)
Zha, H., Zhang, Z.: Continuum Isomap for manifold learnings. Comput. Stat. Data Anal. 52, 184–200 (2007)
Donoho, D., Grimes, C.: Hessian eigenmaps: new tools for nonlinear dimensianality reduction. Proc. Natl. Acad. Sci., 5591–5596 (2003)
Tenenbaum, J.B., Silva, V.D.: Global versus local methods in nonlinear dimensionality reduction. In: Proceeding of Advances in Neural Information Processing Systems 15. MIT Press, Cambridge (2003)
Orsenigo, C.: An improved set covering problem for Isomap supervised landmark selecion. Pattern Recogn. Lett. 49, 131–137 (2014)
Samko, O., Marshall, A.D., Rosin, P.L.: Selection of the optimal parameter value for the Isomap algorithm. Pattern Recogn. Lett. 27, 968–979 (2006)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhang, S., Xie, W. (2017). Nonlinear Dimensionality Reduction via Homeomorphic Tangent Space and Compactness. In: Zou, B., Li, M., Wang, H., Song, X., Xie, W., Lu, Z. (eds) Data Science. ICPCSEE 2017. Communications in Computer and Information Science, vol 727. Springer, Singapore. https://doi.org/10.1007/978-981-10-6385-5_44
Download citation
DOI: https://doi.org/10.1007/978-981-10-6385-5_44
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-6384-8
Online ISBN: 978-981-10-6385-5
eBook Packages: Computer ScienceComputer Science (R0)