Data driven estimation of Laplace-Beltrami operator

Abstract : 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.
Complete list of metadatas

https://hal.inria.fr/hal-01387021
Contributor : Frédéric Chazal <>
Submitted on : Tuesday, October 25, 2016 - 9:20:27 AM
Last modification on : Tuesday, June 18, 2019 - 2:36:02 PM

File

VersionLongue.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01387021, version 1

Citation

Frédéric Chazal, Ilaria Giulini, Bertrand Michel. Data driven estimation of Laplace-Beltrami operator. 30th Conference on Neural Information Processing Systems (NIPS 2016), Dec 2016, Barcelona, Spain. ⟨hal-01387021v1⟩

Share

Metrics

Record views

108

Files downloads

112