Skip to yearly menu bar Skip to main content


Consistency of Dictionary-Based Manifold Learning

Samson Koelle · Hanyu Zhang · Octavian-Vlad Murad · Marina Meila

MR1 & MR2 - Number 52
[ ]
Fri 3 May 8 a.m. PDT — 8:30 a.m. PDT


We analyze a paradigm for interpretable Manifold Learning for scientific data analysis, whereby one parametrizes a manifold with d smooth functions from a scientist-provided dictionary of meaningful, domain-related functions. When such a parametrization exists, we provide an algorithm for finding it based on sparse regression in the manifold tangent bundle, bypassing more standard, agnostic manifold learning algorithms. We prove conditions for the existence of such parameterizations in function space and the first end to end recovery results from finite samples. The method is demonstrated on both synthetic problems and with data from a real scientific domain.

Live content is unavailable. Log in and register to view live content