On the identifiability of interaction functions in systems of interacting particles

Identifiability is of fundamental importance in the statistical learning of dynamical systems of interacting particles. We prove that the interaction functions are identifiable for a class of first-order stochastic systems, including linear systems and a class of nonlinear systems with stationary distributions in the decentralized directions. We show that the identfiability is equivalent to strict positiveness of integral operators associated to integral kernels arisen from the nonparametric regression. We then prove the positiveness based on series representation of the integral kernels and a Muntz type theorem for the completeness of even polynomials.