Towards a theoretical foundation for Laplacian-based manifold methods

2007/08/31 by Mikhail Belkin, Partha Niyogi · 30 citations
Computer Science · #Topological and Geometric Data Analysis #Face and Expression Recognition #Neural Networks and Applications

paper · doi:10.1016/j.jcss.2007.08.006

Cited by

• A Topological View of Unsupervised Learning from Noisy Data
• Behavior of Graph Laplacians on Manifolds with Boundary
• Lipschitz Bounds and Provably Robust Training by Laplacian Smoothing
• The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning
• In-Context Semi-Supervised Learning
• Asymptotics of the graph Laplace operator near an isolated singularity
• STARK denoises spatial transcriptomics images via adaptive regularization
• Approximating Loops in a Shortest Homology Basis from Point Data
• Search at Scale: Improving Numerical Conditioning of Ergodic Coverage Optimization for Multi-Scale Domains
• How do kernel-based sensor fusion algorithms behave under high dimensional noise?
• Decimated Framelet System on Graphs and Fast G-Framelet Transforms
• Extracting manifold information from point clouds
• The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains
• Whole-brain Prediction Analysis with GraphNet
• A tutorial on spectral clustering
• Operator norm convergence of spectral clustering on level sets
• PDE-Free Mass-Constrained Learning of Complex Systems with Hidden States
• Robust Tangent Space Estimation via Laplacian Eigenvector Gradient Orthogonalization
• Noncommutative Laplacian and numerical approximation of Laplace-Beltrami spectrum of compact Riemann surfaces
• When Scores Learn Geometry: Rate Separations under the Manifold Hypothesis
• Entropic Optimal Transport in Random Graphs
• Landing with the Score: Riemannian Optimization through Denoising
• The diffusion geometry of fibre bundles: Horizontal diffusion maps
• High-Dimensional Statistical Process Control via Manifold Fitting and Learning
• Machine learning of slow collective variables and enhanced sampling via spatial techniques
• Optimization of geometric hypergraph embedding
• Connection graph Laplacian methods can be made robust to noise
• DeepSphere: a graph-based spherical CNN
• Deep nets for local manifold learning
• Manifold Regularization for Locally Stable Deep Neural Networks
• Wavelets on graphs via spectral graph theory