Learning Globally Smooth Functions on Manifolds
Abstract
Smoothness and low dimensional structures play central roles in improving generalization and stability in learning and statistics. This work combines techniques from semi-infinite constrained learning and manifold regularization to learn representations that are globally smooth on a manifold. To do so, it shows that under typical conditions the problem of learning a Lipschitz continuous function on a manifold is equivalent to a dynamically weighted manifold regularization problem. This observation leads to a practical algorithm based on a weighted Laplacian penalty whose weights are adapted using stochastic gradient techniques. It is shown that under mild conditions, this method estimates the Lipschitz constant of the solution, learning a globally smooth solution as a byproduct. Experiments on real world data illustrate the advantages of the proposed method relative to existing alternatives.
Cite
@article{arxiv.2210.00301,
title = {Learning Globally Smooth Functions on Manifolds},
author = {Juan Cervino and Luiz F. O. Chamon and Benjamin D. Haeffele and Rene Vidal and Alejandro Ribeiro},
journal= {arXiv preprint arXiv:2210.00301},
year = {2023}
}