Learning Interaction Kernels for Agent Systems on Riemannian Manifolds

Mauro Maggioni · Jason Miller · Hongda Qiu · Ming Zhong

Keywords: [ Learning Theory ] [ Ranking and Preference Learning ] [ Statistical Learning Theory ] [ Algorithms -> Active Learning; Algorithms -> Classification; Algorithms ]

[ Abstract ]
[ Paper ]
[ Visit Poster at Spot A0 in Virtual World ]
Thu 22 Jul 9 a.m. PDT — 11 a.m. PDT
Spotlight presentation: Learning Theory 14
Thu 22 Jul 6 a.m. PDT — 7 a.m. PDT

Abstract: Interacting agent and particle systems are extensively used to model complex phenomena in science and engineering. We consider the problem of learning interaction kernels in these dynamical systems constrained to evolve on Riemannian manifolds from given trajectory data. The models we consider are based on interaction kernels depending on pairwise Riemannian distances between agents, with agents interacting locally along the direction of the shortest geodesic connecting them. We show that our estimators converge at a rate that is independent of the dimension of the state space, and derive bounds on the trajectory estimation error, on the manifold, between the observed and estimated dynamics. We demonstrate the performance of our estimator on two classical first order interacting systems: Opinion Dynamics and a Predator-Swarm system, with each system constrained on two prototypical manifolds, the $2$-dimensional sphere and the Poincar\'e disk model of hyperbolic space.

Chat is not available.