Let \(\mathcal {M}\subseteq \mathbb {R}^d\) denote a low-dimensional manifold and let \(\mathcal {X}= \{ x_1, \dots , x_n \}\) be a collection of points uniformly sampled from \(\mathcal {M}\) . We study the relationship between a notion of curvature of a random geometric graph built from \(\mathcal {X}\) and the curvature of the manifold \(\mathcal {M}\) via continuum limits of Ollivier’s discrete Ricci curvature. By using a suitable distance function on the data cloud \(\mathcal {X}\) to define its Ollivier-Ricci curvature, we are able to prove pointwise, non-asymptotic consistency results and also show that, if \(\mathcal {M}\) has Ricci curvature bounded from below by a positive constant, then the random geometric graph will inherit this global structural property with high probability. We discuss applications of the global discrete curvature bounds to contraction properties of heat kernels on graphs, as well as implications for manifold learning from data clouds. In particular, we show that our consistency results allow for estimating the intrinsic curvature of a manifold by first estimating concrete extrinsic geometric quantities.
