DeepAI AI Chat
Log In Sign Up

Distributed Learning via Filtered Hyperinterpolation on Manifolds

by   Guido Montufar, et al.

Learning mappings of data on manifolds is an important topic in contemporary machine learning, with applications in astrophysics, geophysics, statistical physics, medical diagnosis, biochemistry, 3D object analysis. This paper studies the problem of learning real-valued functions on manifolds through filtered hyperinterpolation of input-output data pairs where the inputs may be sampled deterministically or at random and the outputs may be clean or noisy. Motivated by the problem of handling large data sets, it presents a parallel data processing approach which distributes the data-fitting task among multiple servers and synthesizes the fitted sub-models into a global estimator. We prove quantitative relations between the approximation quality of the learned function over the entire manifold, the type of target function, the number of servers, and the number and type of available samples. We obtain the approximation rates of convergence for distributed and non-distributed approaches. For the non-distributed case, the approximation order is optimal.


page 20

page 21


Distributed filtered hyperinterpolation for noisy data on the sphere

Problems in astrophysics, space weather research and geophysics usually ...

Deep ReLU network approximation of functions on a manifold

Whereas recovery of the manifold from data is a well-studied topic, appr...

Non-Parametric Estimation of Manifolds from Noisy Data

A common observation in data-driven applications is that high dimensiona...

Robust Geodesic Regression

This paper studies robust regression for data on Riemannian manifolds. G...

Behavior of Graph Laplacians on Manifolds with Boundary

In manifold learning, algorithms based on graph Laplacians constructed f...

Data-driven geometric scale detection via Delaunay interpolation

Accurate approximation of a real-valued function depends on two aspects ...

Generalized active learning and design of statistical experiments for manifold-valued data

Characterizing the appearance of real-world surfaces is a fundamental pr...