Tangent Space and Dimension Estimation with the Wasserstein Distance

2021-10-12 · Uzu Lim, Harald Oberhauser, Vidit Nanda

Consider a set of points sampled independently near a smooth compact submanifold of Euclidean space. We provide mathematically rigorous bounds on the number of sample points required to estimate both the dimension and the tangent spaces of that manifold with high confidence. The algorithm for this estimation is Local PCA, a local version of principal component analysis. Our results accommodate for noisy non-uniform data distribution with the noise that may vary across the manifold, and allow simultaneous estimation at multiple points. Crucially, all of the constants appearing in our bound are explicitly described. The proof uses a matrix concentration inequality to estimate covariance matrices and a Wasserstein distance bound for quantifying nonlinearity of the underlying manifold and non-uniformity of the probability measure.

📄 PDF Abstract BibTeX arXiv:2110.06357

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

PCA Principle Components Analysis (PCA) is an unsupervised method primary used for dimensionality reduction within machine learning. PCA is calculated via a singular value…

A Tangent Distance Preserving Dimensionality Reduction Algorithm

2019-02-04 · Xu Zhao, Zongli Jiang

This paper considers the problem of nonlinear dimensionality reduction. Unlike existing methods, such as LLE, ISOMAP, which attempt to unfold the true manifold in the low dimensional space, our algorithm tries to preserv…

Dimensionality Reduction

Neural Local Wasserstein Regression

2025-11-13 · Inga Girshfeld, Xiaohui Chen arxiv

We study the estimation problem of distribution-on-distribution regression, where both predictors and responses are probability measures. Existing approaches typically rely on a global optimal transport map or tangent-sp…

Monge's Optimal Transport Distance for Image Classification

2016-12-01 · Michael Snow, Jan Van lent

This paper focuses on a similarity measure, known as the Wasserstein distance, with which to compare images. The Wasserstein distance results from a partial differential equation (PDE) formulation of Monge's optimal tran…

Classification General Classification image-classification Image Classification

Wasserstein Wormhole: Scalable Optimal Transport Distance with Transformers

2024-04-15 · Doron Haviv, Russell Zhang Kunes, Thomas Dougherty, Cassandra Burdziak 외

Optimal transport (OT) and the related Wasserstein metric (W) are powerful and ubiquitous tools for comparing distributions. However, computing pairwise Wasserstein distances rapidly becomes intractable as cohort size gr…

Decoder

Orthogonal Estimation of Wasserstein Distances

2019-03-09 · Mark Rowland, Jiri Hron, Yunhao Tang, Krzysztof Choromanski 외

Wasserstein distances are increasingly used in a wide variety of applications in machine learning. Sliced Wasserstein distances form an important subclass which may be estimated efficiently through one-dimensional sortin…

BIG-bench Machine Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)