Crown complementarity rather than crown selection contributes to stem complementarity in genetic mixtures of Pinus taeda L

Carter, David R; Albaugh, Timothy J; Sumnall, Matthew; Grossman, Jake J; Campoe, Otávio C; Cook, Rachel L; Rubilar, Rafael A; Maier, Chris A; Coates, T Adam; DeFeo, Julia; Boyle, Grady J; Van_Spanje, Megan

doi:10.1016/j.actao.2025.104058

This paper investigates the learning, or system identification, of a class of piecewise-affine dynamical systems known as linear complementarity systems (LCSs). We propose a violation-based loss which enables efficient learning of the LCS parameterization, without prior knowledge of the hybrid mode boundaries, using gradient-based methods. The proposed violation-based loss incorporates both dynamics prediction loss and a novel complementarity - violation loss. We show several properties attained by this loss formulation, including its differentiability, the efficient computation of first- and second-order derivatives, and its relationship to the traditional prediction loss, which strictly enforces complementarity. We apply this violation-based loss formulation to learn LCSs with tens of thousands of (potentially stiff) hybrid modes. The results demonstrate a state-of-the-art ability to identify piecewise-affine dynamics, outperforming methods which must differentiate through non-smooth linear complementarity problems.

More Like this