We study the game theoretic p-Laplacian for semi-supervised learning on graphs, and show that it is well-posed in the limit of finite labeled data and infinite unlabeled data. In particular, we show that the continuum limit of graph-based semi-supervised learning with the game theoretic p-Laplacian is a weighted version of the continuous p-Laplace equation. We also prove that solutions to the graph p-Laplace equation are approximately Hölder continuous with high probability. Our proof uses the viscosity solution machinery and the maximum principle on a graph.
Bibliographical noteFunding Information:
The author gratefully acknowledges the support of NSF-DMS grant 1713691. The author is also grateful to the anonymous referees, whose suggestions have greatly improved the paper.
© 2018 IOP Publishing Ltd & London Mathematical Society.
- continuum limit
- game theoretic p-Laplacian
- maximum principle
- semi-supervised learning
- viscosity solutions