no code implementations • 21 Feb 2024 • Yongcun Song, Ziqi Wang, Enrique Zuazua
First, we design an inexactness criterion for the clients' local updates to eliminate the need for empirically setting the local training accuracy.
no code implementations • 13 Aug 2023 • Yongcun Song, Ziqi Wang, Enrique Zuazua
Federated Learning (FL) is a distributed learning paradigm that enables multiple clients to collaborate on building a machine learning model without sharing their private data.
1 code implementation • 13 Aug 2023 • Ming-Chih Lai, Yongcun Song, Xiaoming Yuan, Hangrui Yue, Tianyou Zeng
We show that the physics-informed neural networks (PINNs), in combination with some recently developed discontinuity capturing neural networks, can be applied to solve optimal control problems subject to partial differential equations (PDEs) with interfaces and some control constraints.
no code implementations • 1 Jul 2023 • Yongcun Song, Xiaoming Yuan, Hangrui Yue
The accelerated primal-dual method with operator learning is mesh-free, numerically efficient, and scalable to different types of PDEs.
no code implementations • 7 Jan 2021 • Roland Glowinski, Yongcun Song, Xiaoming Yuan, Hangrui Yue
However, due to the additional divergence-free constraint on the control variable and the nonlinear relation between the state and control variables, it is challenging to compute the gradient and the optimal stepsize at each CG iteration, and thus nontrivial to implement the CG method.
Optimization and Control 49M41, 35Q93, 49J20