Search

Solving semiparametric models can be computationally challenging because the dimension of parameter space may grow large with increasing sample size. Classical Newton's method becomes quite slow and unstable with an intensive calculation of the large Hessian matrix and its inverse. Iterative methods separately updating parameters for the finite dimensional component and the infinite dimensional component have been developed to speed up single iterations, but they often take more steps until convergence or even sometimes sacrifice estimation precision due to sub-optimal update direction. We propose a computationally efficient implicit profiling algorithm that achieves simultaneously the fast iteration step in iterative methods and the optimal update direction in Newton's method by profiling out the infinite dimensional component as the function of the finite-dimensional component. We devise a first-order approximation when the profiling function has no explicit analytical form. We show that our implicit profiling method always solves any local quadratic programming problem in two steps. In two numerical experiments under semiparametric transformation models and GARCH-M models, as well as a real application using NTP data, we demonstrated the computational efficiency and statistical precision of our implicit profiling method. Finally, we implement the proposed implicit profiling method in the R package SemiEstimate [ABSTRACT FROM AUTHOR]

Accurate and timely assessment of post-disaster building damage is of great significance for national development and social security concerns. However, due to the high timeliness requirements of disaster emergency response and the conflict that sufficient computing resources are not easily available in harsh environments, and therefore the lightweight AI-driven post-disaster building damage assessment model is highly needed. In this paper, we introduced a knowledge distillation-based lightweight approach for assessing building damage from xBD high-resolution satellite images with the purpose of reducing the dependence on computing resources in disaster emergency response scenarios. Specifically, an ensemble Teacher-Student knowledge distillation method was designed and compared with the xBD baseline model. The result has shown that, the knowledge distillation reduces the parameter number of the original model by 30%, and the inference speed is increased by 30%-40%. In the building localization task, the accuracy of teacher and student model are 0.879 and 0.832 (IOU) respectively. In the damage classification task, the accuracy of teacher and student are 0.798 and 0.775 respectively. In addition, we proposed a dual-teacher-student knowledge distillation strategy, which cannot use the pre-training skills of curriculum learning in student model training, but achieve the same effect through more direct knowledge transfer. In the experiment, our dual-teacher-student method improves the knowledge distillation baseline by 3.7% with 30 epoch training. With only 70% parameters, our student model performs close to the teacher model at a degradation within 5%.This study verifies the effectiveness and prospect of knowledge distillation method in building damage assessment for disaster emergency. [ABSTRACT FROM AUTHOR]