Smooth function extension based on high dimensional unstructured data

Author:

Chui Charles,Mhaskar H.

Abstract

Many applications, including the image search engine, image inpainting, hyperspectral image dimensionality reduction, pattern recognition, and time series prediction, can be facilitated by considering the given discrete data–set as a point-cloud P {\mathcal P} in some high dimensional Euclidean space R s {\mathbb R}^{s} . Then the problem is to extend a desirable objective function f f from a certain relatively smaller training subset C P \mathcal {C}\subset {\mathcal P} to some continuous manifold X R s {\mathbb X}\subset {\mathbb R}^{s} that contains P {\mathcal P} , at least approximately. More precisely, when the point cloud P {\mathcal P} of the given data–set is modeled in the abstract by some unknown compact manifold embedded in the ambient Euclidean space R s {\mathbb R}^{s} , the extension problem can be considered as the interpolation problem of seeking the objective function on the manifold X {\mathbb X} that agrees with f f on C \mathcal {C} under certain desirable specifications. For instance, by considering groups of cardinality s s of data values as points in a point-cloud in R s {\mathbb R}^{s} , such groups that are far apart in the original spatial data domain in R 1 {\mathbb R}^{1} or R 2 {\mathbb R}^{2} , but have similar geometric properties, can be arranged to be close neighbors on the manifold. The objective of this paper is to incorporate the consideration of data geometry and spatial approximation, with immediate implications to the various directions of application areas. Our main result is a point-cloud interpolation formula that provides a near-optimal degree of approximation to the target objective function on the unknown manifold.

Publisher

American Mathematical Society (AMS)

Subject

Applied Mathematics,Computational Mathematics,Algebra and Number Theory

Reference35 articles.

1. M. Belkin and P. Niyogi, Semi-supervised learning on Riemannian manifolds, Machine Learning Journal 56 (2004), 209–239.

2. Towards a theoretical foundation for Laplacian-based manifold methods;Belkin, Mikhail;J. Comput. System Sci.,2008

3. M. Belkin, P. Niyogi, Convergence of Laplacian Eigenmaps, Manuscript (http://www. cse.ohio-state.edu/ mbelkin/papers/CLEM_08.pdf).

4. A general framework for local interpolation;Chui, Charles K.;Numer. Math.,1991

5. MRA contextual-recovery extension of smooth functions on manifolds;Chui, Charles K.;Appl. Comput. Harmon. Anal.,2010

Cited by 8 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Deep Nets for Local Manifold Learning;Frontiers in Applied Mathematics and Statistics;2018-05-29

2. A unified framework for harmonic analysis of functions on directed graphs and changing data;Applied and Computational Harmonic Analysis;2018-05

3. Metric entropy, n-widths, and sampling of functions on manifolds;Journal of Approximation Theory;2018-01

4. Local Approximation Using Hermite Functions;Springer Optimization and Its Applications;2017

5. WITHDRAWN: An efficient multiscale algorithm;Applied and Computational Harmonic Analysis;2016-07

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3