Identifiability of interaction kernels in mean-field equations of interacting particles
This work addresses identifiability issues in interacting particle systems, which are important for scientific and engineering applications, but it is incremental as it builds on prior research to complete a full characterization.
The study tackled the problem of identifying interaction kernels in mean-field equations of interacting particles by characterizing data-dependent function spaces where a quadratic loss functional has a unique minimizer, showing that the weighted L^2 space yields more accurate regularized estimators in numerical demonstrations.
This study examines the identifiability of interaction kernels in mean-field equations of interacting particles or agents, an area of growing interest across various scientific and engineering fields. The main focus is identifying data-dependent function spaces where a quadratic loss functional possesses a unique minimizer. We consider two data-adaptive $L^2$ spaces: one weighted by a data-adaptive measure and the other using the Lebesgue measure. In each $L^2$ space, we show that the function space of identifiability is the closure of the RKHS associated with the integral operator of inversion. Alongside prior research, our study completes a full characterization of identifiability in interacting particle systems with either finite or infinite particles, highlighting critical differences between these two settings. Moreover, the identifiability analysis has important implications for computational practice. It shows that the inverse problem is ill-posed, necessitating regularization. Our numerical demonstrations show that the weighted $L^2$ space is preferable over the unweighted $L^2$ space, as it yields more accurate regularized estimators.