Poster
Data driven estimation of Laplace-Beltrami operator
Frederic Chazal · Ilaria Giulini · Bertrand Michel
Area 5+6+7+8 #27
Keywords: [ Spectral Methods ] [ (Other) Statistics ] [ Graph-based Learning ] [ Nonlinear Dimension Reduction and Manifold Learning ]
Approximations of Laplace-Beltrami operators on manifolds through graph Laplacians 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 unormalized 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 (2015) on the so-called Lepski's method.
Live content is unavailable. Log in and register to view live content