Adaptive Geometric Multiscale Approximations for Intrinsically Low-dimensional Data

by   Wenjing Liao, et al.

We consider the problem of efficiently approximating and encoding high-dimensional data sampled from a probability distribution ρ in R^D, that is nearly supported on a d-dimensional set M - for example supported on a d-dimensional Riemannian manifold. Geometric Multi-Resolution Analysis (GMRA) provides a robust and computationally efficient procedure to construct low-dimensional geometric approximations of M at varying resolutions. We introduce a thresholding algorithm on the geometric wavelet coefficients, leading to what we call adaptive GMRA approximations. We show that these data-driven, empirical approximations perform well, when the threshold is chosen as a suitable universal function of the number of samples n, on a wide variety of measures ρ, that are allowed to exhibit different regularity at different scales and locations, thereby efficiently encoding data from more complex measures than those supported on manifolds. These approximations yield a data-driven dictionary, together with a fast transform mapping data to coefficients, and an inverse of such a map. The algorithms for both the dictionary construction and the transforms have complexity C n n with the constant linear in D and exponential in d. Our work therefore establishes adaptive GMRA as a fast dictionary learning algorithm with approximation guarantees. We include several numerical experiments on both synthetic and real data, confirming our theoretical results and demonstrating the effectiveness of adaptive GMRA.


page 5

page 12

page 22

page 25


Multiscale regression on unknown manifolds

We consider the regression problem of estimating functions on ℝ^D but su...

Multiscale Geometric Methods for Data Sets II: Geometric Multi-Resolution Analysis

Data sets are often modeled as point clouds in R^D, for D large. It is o...

Decentralized Complete Dictionary Learning via ℓ^4-Norm Maximization

With the rapid development of information technologies, centralized data...

Compressed Dictionary Learning

In this paper we show that the computational complexity of the Iterative...

Learning the nonlinear geometry of high-dimensional data: Models and algorithms

Modern information processing relies on the axiom that high-dimensional ...

Enhanced Multi-Resolution Analysis for Multi-Dimensional Data Utilizing Line Filtering Techniques

In this article we introduce Line Smoothness-Increasing Accuracy-Conserv...

A fast Gauss transform in one dimension using sum-of-exponentials approximations

We present a fast Gauss transform in one dimension using nearly optimal ...

Please sign up or login with your details

Forgot password? Click here to reset