2 papers
cs.LG2025
Physics-Informed Design of Input Convex Neural Networks for Consistency Optimal Transport Flow Matching
Fanghui Song, Zhongjian Wang, Jiebao Sun
We propose a consistency model based on the optimal-transport flow. A physics-informed design of partially input-convex neural networks (PICNN) plays a central role in constructing…
math.OC2025
Distributed Time-Varying Optimization via Unbiased Extremum Seeking
Xuebin Li, Xuefei Yang, Emilia Fridman +2
This paper proposes a novel distributed optimization framework that addresses time-varying optimization problems without requiring explicit derivative information of the objective…