Gaussian Process Landmarking on Manifolds
This improves biological shape analysis by providing a more efficient landmarking method, though it is incremental as it builds on existing greedy strategies and experimental design literature.
The paper tackles the problem of sampling Riemannian manifolds for biological shape analysis by proposing a greedy algorithm that selects points with maximum uncertainty under a Gaussian process model, showing it outperforms user-placed landmarks and establishing an upper bound for mean squared prediction error that decays at a rate comparable to an oracle optimal design.
As a means of improving analysis of biological shapes, we propose an algorithm for sampling a Riemannian manifold by sequentially selecting points with maximum uncertainty under a Gaussian process model. This greedy strategy is known to be near-optimal in the experimental design literature, and appears to outperform the use of user-placed landmarks in representing the geometry of biological objects in our application. In the noiseless regime, we establish an upper bound for the mean squared prediction error (MSPE) in terms of the number of samples and geometric quantities of the manifold, demonstrating that the MSPE for our proposed sequential design decays at a rate comparable to the oracle rate achievable by any sequential or non-sequential optimal design; to our knowledge this is the first result of this type for sequential experimental design. The key is to link the greedy algorithm to reduced basis methods in the context of model reduction for partial differential equations. We expect this approach will find additional applications in other fields of research.