Discovery of interaction and diffusion kernels in particle-to-mean-field multi-agent systems

ArXi:2603.15927v1 Announce Type: new We propose a data-driven framework to learn interaction kernels in stochastic multi-agent systems. Our approach aims at identifying the functional form of nonlocal interaction and diffusion terms directly from trajectory data, without any a priori knowledge of the underlying interaction structure. Starting from a discrete stochastic binary-interaction model, we formulate the inverse problem as a sequence of sparse regression tasks in structured finite-dimensional spaces spanned by compactly ed basis functions, such as piecewise linear polynomials.