Uniform Convergence Rates for Lipschitz Learning on Graphs

Abstract

Lipschitz learning is a graph-based semi-supervised learning method where one extends labels from a labeled to an unlabeled data set by solving the infinity Laplace equation on a weighted graph. In this work we prove uniform convergence rates for solutions of the graph infinity Laplace equation as the number of vertices grows to infinity. Their continuum limits are absolutely minimizing Lipschitz extensions with respect to the geodesic metric of the domain where the graph vertices are sampled from. We work under very general assumptions on the graph weights, the set of labeled vertices, and the continuum domain. Our main contribution is that we obtain quantitative convergence rates even for very sparsely connected graphs, as they typically appear in applications like semi-supervised learning. In particular, our framework allows for graph bandwidths down to the connectivity radius. For proving this we first show a quantitative convergence statement for graph distance functions to geodesic distance functions in the continuum. Using the "comparison with distance functions" principle, we can pass these convergence statements to infinity harmonic functions and absolutely minimizing Lipschitz extensions.

References in corpus (6)

• Consistency of spectral clustering
• On natural invariant measures on generalised iterated function systems
• Poisson Learning: Graph Based Semi-Supervised Learning At Very Low Label Rates
• Algorithms for Lipschitz Learning on Graphs
• Continuum Limit of Lipschitz Learning on Graphs
• Rates of Convergence for Laplacian Semi-Supervised Learning with Low Labeling Rates

Cited by in corpus (6)

• Continuum Limit of Lipschitz Learning on Graphs
• The Infinity Laplacian eigenvalue problem: reformulation and a numerical scheme
• Ratio convergence rates for Euclidean first-passage percolation: Applications to the graph infinity Laplacian
• A mean curvature flow arising in adversarial training
• The convergence rate of $p$-harmonic to infinity-harmonic functions
• Adversarial flows: A gradient flow characterization of adversarial attacks