Distributed Learning via Filtered Hyperinterpolation on Manifolds

Guido Montúfar and Yu Guang Wang

Contact the author: Please use for correspondence this email.
Submission date: 18. Jul. 2020 (revised version: July 2020)
Pages: 52
Bibtex
Keywords and phrases: Distributed learning, Filtered hyperinterpolation, Approximation on manifolds, Kernel methods, Numerical integration on manifolds, Quadrature rule, Random sampling, Gaussian white noise
Download full preprint: PDF (1673 kB)

Abstract:
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.