Data driven estimation of Laplace-Beltrami operator

Approximations of Laplace-Beltrami operators on manifolds through graph Lapla-cians have become popular tools in data analysis and machine learning. These discretized operators usually depend on bandwidth parameters whose tuning remains a theoretical and practical problem. In this paper, we address this problem for the unnormalized graph Laplacian by establishing an oracle inequality that opens the door to a well-founded data-driven procedure for the bandwidth selection. Our approach relies on recent results by Lacour and Massart [LM15] on the so-called Lepski's method.

[1]  P. Massart,et al.  Minimal Penalties for Gaussian Model Selection , 2007 .

[2]  Pascal Massart,et al.  Estimator Selection: a New Method with Applications to Kernel Density Estimation , 2016, Sankhya A.

[3]  Mikhail Belkin,et al.  Semi-Supervised Learning on Riemannian Manifolds , 2004, Machine Learning.

[4]  O. Lepskii.  Asymptotically Minimax Adaptive Estimation. I: Upper Bounds. Optimally Adaptive Estimates , 1992 .

[5]  Sylvain Arlot,et al.  A survey of cross-validation procedures for model selection , 2009, 0907.4728.

[6]  S. Rosenberg.  The Laplacian on a Riemannian Manifold: An Introduction to Analysis on Manifolds , 1997 .

[7]  O. Lepskii,et al.  On problems of adaptive estimation in white Gaussian noise , 1992 .

[8]  Bertrand Michel,et al.  Slope heuristics: overview and implementation , 2011, Statistics and Computing.

[9]  Mikhail Belkin,et al.  Convergence of Laplacian Eigenmaps , 2006, NIPS.

[10]  E. Mammen,et al.  Optimal spatial adaptation to inhomogeneous smoothness: an approach based on kernel estimates with variable bandwidth selectors , 1997 .

[11]  A. Grigor’yan.  Heat Kernel and Analysis on Manifolds , 2012 .

[12]  Ulrike von Luxburg,et al.  Graph Laplacians and their Convergence on Random Neighborhood Graphs , 2006, J. Mach. Learn. Res..

[13]  Pascal Massart,et al.  Data-driven Calibration of Penalties for Least-Squares Regression , 2008, J. Mach. Learn. Res..

[14]  Mikhail Belkin,et al.  Laplacian Eigenmaps for Dimensionality Reduction and Data Representation , 2003, Neural Computation.

[15]  Ling Huang,et al.  An Analysis of the Convergence of Graph Laplacians , 2010, ICML.

[16]  O. Lepskii,et al.  Asymptotically minimax adaptive estimation. II: Schemes without optimal adaptation: adaptive estimators , 1993 .

[17]  Pascal Massart,et al.  Minimal penalty for Goldenshluger-Lepski method , 2015, 1503.00946.

[18]  Antonio Rieser,et al.  A Topological Approach to Spectral Clustering , 2015, Foundations of Data Science.

[19]  V. Koltchinskii,et al.  Empirical graph Laplacian approximation of Laplace–Beltrami operators: Large sample results , 2006, math/0612777.

[20]  B. Nadler,et al.  Diffusion maps, spectral clustering and reaction coordinates of dynamical systems , 2005, math/0503445.

[21]  O. Lepski,et al.  Structural adaptation via Lp-norm oracle inequalities , 2007, 0704.2492.

[22]  Mikhail Belkin,et al.  Towards a theoretical foundation for Laplacian-based manifold methods , 2005, J. Comput. Syst. Sci..

[23]  Ulrike von Luxburg,et al.  A tutorial on spectral clustering , 2007, Stat. Comput..

[24]  Mikhail Belkin,et al.  Consistency of spectral clustering , 2008, 0804.0678.