Consistency of Semi-supervised Learning, Stochastic Tug-of-War Games, and the p-Laplacian
Document Type
Article
Publication Date
1-1-2024
Abstract
In this paper, we give a broad overview of the intersection of partial differential equations (PDEs) and graph-based semi-supervised learning. The overview is focused on a large body of recent work on PDE continuum limits of graph-based learning, which have been used to prove well-posedness of semi-supervised learning algorithms in the large data limit. We highlight some interesting research directions revolving around consistency of graph-based semi-supervised learning and present some new results on the consistency of p-Laplacian semi-supervised learning using the stochastic tug-of-war game interpretation of the p-Laplacian. We also present the results of some numerical experiments that illustrate our results and suggest directions for future work.
Publication Source (Journal or Book title)
Modeling and Simulation in Science Engineering and Technology
First Page
1
Last Page
53
Recommended Citation
Calder, J., & Drenska, N. (2024). Consistency of Semi-supervised Learning, Stochastic Tug-of-War Games, and the p-Laplacian. Modeling and Simulation in Science Engineering and Technology, Part F3944, 1-53. https://doi.org/10.1007/978-3-031-73423-6_1