Non-linear independent component analysis with diffusion maps

DOI10.1016/j.acha.2007.11.001zbMath1144.62044OpenAlexW1972265435WikidataQ125854987 ScholiaQ125854987MaRDI QIDQ942156

Amit Singer, Ronald R. Coifman

Publication date: 4 September 2008

Published in: Applied and Computational Harmonic Analysis (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.acha.2007.11.001

zbMATH Keywords

Fokker-Planck operator

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Inference from stochastic processes (62M99) Applications of stochastic analysis (to PDEs, etc.) (60H30) Applications of Brownian motions and diffusion theory (population genetics, absorption problems, etc.) (60J70)

Related Items (31)

Local kernels and the geometric structure of data ⋮ On the Relation of Slow Feature Analysis and Laplacian Eigenmaps ⋮ Learning from patches by efficient spectral decomposition of a structured kernel ⋮ Unnamed Item ⋮ Data-Driven Reduction for a Class of Multiscale Fast-Slow Stochastic Dynamical Systems ⋮ Local conformal autoencoder for standardized data coordinates ⋮ Multi-view kernel consensus for data analysis ⋮ Generative Stochastic Modeling of Strongly Nonlinear Flows with Non-Gaussian Statistics ⋮ GANs and Closures: Micro-Macro Consistency in Multiscale Modeling ⋮ Anisotropic diffusion on sub-manifolds with application to Earth structure classification ⋮ Manifold learning for accelerating coarse-grained optimization ⋮ Variable bandwidth diffusion kernels ⋮ Computing committors in collective variables via Mahalanobis diffusion maps ⋮ Spatiotemporal analysis using Riemannian composition of diffusion operators ⋮ Functional diffusion maps ⋮ ADM-CLE Approach for Detecting Slow Variables in Continuous Time Markov Chains and Dynamic Data ⋮ A Geometric Approach to the Transport of Discontinuous Densities ⋮ Transport Map Accelerated Adaptive Importance Sampling, and Application to Inverse Problems Arising from Multiscale Stochastic Reaction Networks ⋮ Manifold learning for organizing unstructured sets of process observations ⋮ Learning the geometry of common latent variables using alternating-diffusion ⋮ Parsimonious representation of nonlinear dynamical systems through manifold learning: a chemotaxis case study ⋮ Bigeometric organization of deep nets ⋮ Iterated diffusion maps for feature identification ⋮ Diffusion maps tailored to arbitrary non-degenerate Itô processes ⋮ Connecting dots: from local covariance to empirical intrinsic geometry and locally linear embedding ⋮ Embeddings of Riemannian manifolds with finite eigenvector fields of connection Laplacian ⋮ Explore Intrinsic Geometry of Sleep Dynamics and Predict Sleep Stage by Unsupervised Learning Techniques ⋮ A Geometrical Method for Low-Dimensional Representations of Simulations ⋮ Diffusion nets ⋮ Data-driven spectral decomposition and forecasting of ergodic dynamical systems ⋮ Intrinsic modeling of stochastic dynamical systems using empirical geometry

Uses Software

• FastICA

Cites Work

• Diffusion maps
• Diffusion maps, spectral clustering and reaction coordinates of dynamical systems
• Spectral independent component analysis
• Feasibility of tomography with unknown view angles
• Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
• Graph Laplacian Tomography From Unknown Random Projections
• Hessian eigenmaps: Locally linear embedding techniques for high-dimensional data
• Learning Theory

This page was built for publication: Non-linear independent component analysis with diffusion maps