Testing the manifold hypothesis

DOI10.1090/JAMS/852MaRDI QIDQ5741444zbMATH OpenOpenAlexFDO

Authors Hariharan Narayanan, Charles Fefferman, Sanjoy K. Mitter

Publication date 25 July 2016

Published in Journal of the American Mathematical Society (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1310.0425

zbMATH Keywords

dimension reductionmanifold learningmanifold estimationprincipal manifolds

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Learning and adaptive systems in artificial intelligence (68T05) Hypothesis testing in multivariate analysis (62H15) Embeddings in differential topology (57R40) Fiber bundles in algebraic topology (55R10)

Abstract: The hypothesis that high dimensional data tend to lie in the vicinity of a low dimensional manifold is the basis of manifold learning. The goal of this paper is to develop an algorithm (with accompanying complexity guarantees) for fitting a manifold to an unknown probability distribution supported in a separable Hilbert space, only using i.i.d samples from that distribution. More precisely, our setting is the following. Suppose that data are drawn independently at random from a probability distribution $P$ supported on the unit ball of a separable Hilbert space $H$. Let $G(d,V,au)$ be the set of submanifolds of the unit ball of $H$ whose volume is at most $V$ and reach (which is the supremum of all $r$ such that any point at a distance less than $r$ has a unique nearest point on the manifold) is at least $au$. Let $L(M,P)$ denote mean-squared distance of a random point from the probability distribution $P$ to $M$. We obtain an algorithm that tests the manifold hypothesis in the following sense. The algorithm takes i.i.d random samples from $P$ as input, and determines which of the following two is true (at least one must be): (a) There exists $MinG(d,CV,fracauC)$ such that $L(M,P)leqCepsilon.$ (b) There exists no $MinG(d,V/C,Cau)$ such that $L(M,P)leqfracepsilonC.$ The answer is correct with probability at least $1-delta$.

Recommendations

• Minimax rates for estimating the dimension of a manifold
• Finding the homology of submanifolds with high confidence from random samples
• Learning gradients on manifolds
• Sampling from a Manifold
• Shape dimension and intrinsic metric from samples of manifolds with high co-dimension (extended abstract)

Cites work

• scientific article; zbMATH DE number 499496 (Why is no real title available?)
• scientific article; zbMATH DE number 1560711 (Why is no real title available?)
• scientific article; zbMATH DE number 847265 (Why is no real title available?)
• scientific article; zbMATH DE number 893887 (Why is no real title available?)
• scientific article; zbMATH DE number 5485566 (Why is no real title available?)
• K-Dimensional Coding Schemes in Hilbert Spaces
• A new algorithm for minimizing convex functions over convex sets
• Advanced Lectures on Machine Learning
• Approximation of points on low-dimensional manifolds via random linear projections
• Combinatorics of random processes and sections of convex bodies
• Curvature Measures
• Estimation of dependences based on empirical data. Transl. from the Russian by Samuel Kotz
• Extensions of Lipschitz mappings into a Hilbert space
• Finding the homology of submanifolds with high confidence from random samples
• Geometric diffusions as a tool for harmonic analysis and structure definition of data: multiscale methods
• Hessian eigenmaps: Locally linear embedding techniques for high-dimensional data
• Infinite-dimensional manifolds of finite-entropy probability measures
• Interpolation and extrapolation of smooth functions by linear operators
• Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
• Lectures on topics in analysis. Notes by M. S. Rajwade
• Locally defined principal curves and surfaces
• Manifold estimation and singular deconvolution under Hausdorff loss
• Manifold reconstruction from point samples
• Manifold reconstruction in arbitrary dimensions using witness complexes
• Minimax manifold estimation
• Nonparametric ridge estimation
• Principal Curves
• Principal Manifolds and Nonlinear Dimensionality Reduction via Tangent Space Alignment
• Random projections of smooth manifolds
• Robust recovery of multiple subspaces by geometric \(l_{p}\) minimization
• Some applications of concentration inequalities to statistics
• The C^m norm of a function with prescribed jets. II
• The concentration of measure phenomenon
• Tighter bounds for random projections of manifolds
• Topology and data
• Uniform Central Limit Theorems
• Universal local parametrizations via heat kernels and eigenfunctions of the Laplacian
• \(k\)-plane clustering

Cited in

(only showing first 100 items - show all)

• Low dimensional approximation and generalization of multivariate functions on smooth manifolds using deep ReLU neural networks
• A Metric Space for Point Process Excitations
• Manifold learning in Wasserstein space
• Metric thickenings of Euclidean submanifolds
• Inverse problems on low-dimensional manifolds
• Unsupervised solution operator learning for mean-field games
• Fitting a manifold of large reach to noisy data
• Reconstruction of a Riemannian manifold from noisy intrinsic distances
• Mitigating distribution shift in machine learning-augmented hybrid simulation
• Occupants in manifolds
• Uncertainty quantification in cost-effectiveness analysis for stochastic-based infectious disease models: insights from surveillance on lymphatic filariasis
• Density estimation on an unknown submanifold
• Interpolation, the rudimentary geometry of spaces of Lipschitz functions, and geometric complexity
• Model-Centric Data Manifold: The Data Through the Eyes of the Model
• Deep nonparametric estimation of intrinsic data structures by chart autoencoders: generalization error and robustness
• On boundary detection
• An adaptive and stability-promoting layerwise training approach for sparse deep neural network architecture
• Universally consistent estimation of the reach
• Topological reconstruction of compact supports of dependent stationary random variables
• Manifold fitting under unbounded noise
• Finding the homology of submanifolds with high confidence from random samples
• Recovery of Surfaces and Functions in High Dimensions: Sampling Theory and Links to Neural Networks
• Approximation by non-symmetric networks for cross-domain learning
• Reconstruction and interpolation of manifolds. I: The geometric Whitney problem
• Ricci curvature and the manifold learning problem
• Optimal convergence rates for the spectrum of the graph Laplacian on Poisson point clouds
• Optimal 1-Wasserstein distance for WGANs
• Adversarial attacks on neural networks through canonical Riemannian foliations
• Normal-bundle bootstrap
• Deep nonparametric regression on approximate manifolds: nonasymptotic error bounds with polynomial prefactors
• Deep learning of thermodynamics-aware reduced-order models from data
• Tangent space and dimension estimation with the Wasserstein distance
• Megaman: scalable manifold learning in Python
• Wassmap: Wasserstein Isometric Mapping for Image Manifold Learning
• IAN: Iterated Adaptive Neighborhoods for Manifold Learning and Dimensionality Estimation
• Data analysis from empirical moments and the Christoffel function
• A universal law of robustness via isoperimetry
• Accelerating phase-field predictions via recurrent neural networks learning the microstructure evolution in latent space
• Robust \(k\)-means clustering for distributions with two moments
• Discretized gradient flow for manifold learning
• Persistent intersection homology for the analysis of discrete data
• Markov spin models for image generation: explicit large deviations with respect to the number of pixels
• On consistent estimation of dimension values
• Enabling probabilistic learning on manifolds through double diffusion maps
• Method of moments for estimation of noisy curves
• Effective theory building and manifold learning
• Minimax rates for estimating the dimension of a manifold
• Osculating geometry and higher-order distance loci
• Mode and Ridge Estimation in Euclidean and Directional Product Spaces: A Mean Shift Approach
• Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Reply to the discussion of: ``Statistical exploration of the manifold hypothesis
• Algebraic machine learning with an application to chemistry
• Random Fixed Boundary Flows
• Riemannian integrated gradients: a geometric view of explainable AI
• Localized Schrödinger bridge sampler
• Geometric anomaly detection in data
• Reconstruction of dynamical systems without time label
• Applications of No-Collision Transportation Maps in Manifold Learning
• Dimensionality reduction for \(k\)-distance applied to persistent homology
• Estimating a density near an unknown manifold: a Bayesian nonparametric approach
• Deep generative models: complexity, dimensionality, and approximation
• Data-driven spatiotemporal modeling for structural dynamics on irregular domains by stochastic dependency neural estimation
• Nonasymptotic bounds for forward processes in denoising diffusions: Ornstein-Uhlenbeck is hard to beat
• Pursuit of a discriminative representation for multiple subspaces via sequential games
• Side effects of learning from low-dimensional data embedded in a Euclidean space
• Bayesian Imaging with Data-Driven Priors Encoded by Neural Networks
• A Whitney extension problem for manifolds
• Deep Mutual Density Ratio Estimation with Bregman Divergence and Its Applications
• Reconstruction and interpolation of manifolds. II: Inverse problems with partial data for distances observations and for the heat kernel

This page was built for publication: Testing the manifold hypothesis

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5741444)