A Mean Curvature Approach to Boundary Detection: Geometric Insights for Unsupervised Learning
About
Accurate boundary detection in high-dimensional data remains a central challenge in unsupervised learning, particularly in the presence of non-linear structures and heterogeneous densities. In this work, we introduce Mean Curvature Boundary Points (MCBP), a novel geometric framework grounded in Geometric Machine Learning that departs from traditional density-based approaches by explicitly modeling the intrinsic curvature of the data manifold. The method relies on a discrete approximation of the shape operator, estimated from local k-nearest neighbor patches, to compute pointwise mean curvature without requiring explicit manifold parametrization. The key insight of MCBP is to use mean curvature as a principled descriptor of boundary structure: high-curvature regions naturally correspond to transitions between clusters, geometric irregularities, and low-density interfaces. This yields a unified geometric interpretation of boundary, outlier, and transition points. We further introduce an adaptive percentile-based thresholding scheme that enables multiscale boundary extraction without relying on ad hoc density parameters. Beyond detection, we propose a curvature-driven data decomposition that separates samples into smooth (low-curvature) and boundary (high-curvature) subsets, effectively acting as a non-linear geometric filtering mechanism. This representation enhances cluster separability and improves the robustness of downstream unsupervised algorithms. Extensive experiments on synthetic and real-world datasets demonstrate that MCBP consistently improves clustering performance, particularly in complex and high-dimensional scenarios. These results position MCBP as a concrete contribution to Geometric Machine Learning, highlighting the potential of curvature-aware analysis as a unifying paradigm bridging differential geometry and data-driven modeling.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Local Curvature Estimation | SATIMAGE | Average Local Curvature1.1526 | 4 | |
| Local Curvature Estimation | Iris | Average Local Curvature0.1645 | 2 | |
| Local Curvature Estimation | SEEDS | Average Local Curvature0.4641 | 2 | |
| Local Curvature Estimation | Page-blocks | Average Local Curvature0.4168 | 2 | |
| Local Curvature Estimation | Hill Valley | Average Local Curvature0.8479 | 2 | |
| Local Curvature Estimation | Cardiotocography | Average Local Curvature3.4287 | 2 | |
| Local Curvature Estimation | artificial-characters | Average Local Curvature0.1192 | 2 | |
| Local Curvature Estimation | qsar-biodeg | Average local curvature4.7824 | 2 | |
| Local Curvature Estimation | steel-plates-fault | Average Local Curvature2.5691 | 2 | |
| Local Curvature Estimation | eye_movements | Average Local Curvature3.5541 | 2 |