3 papers
math.OC2025
On Representing Convex Quadratically Constrained Quadratic Programs via Graph Neural Networks
Chenyang Wu, Qian Chen, Akang Wang +4
Convex quadratically constrained quadratic programs (QCQPs) involve finding a solution within a convex feasible region defined by quadratic constraints while minimizing a convex qu…
math.OC2024
Mixed-Integer Linear Optimization via Learning-Based Two-Layer Large Neighborhood Search
Wenbo Liu, Akang Wang, Wenguo Yang +1
Mixed-integer linear programs (MILPs) are extensively used to model practical problems such as planning and scheduling. A prominent method for solving MILPs is large neighborhood s…
math.OC2024
IPM-LSTM: A Learning-Based Interior Point Method for Solving Nonlinear Programs
Xi Gao, Jinxin Xiong, Akang Wang +3
Solving constrained nonlinear programs (NLPs) is of great importance in various domains such as power systems, robotics, and wireless communication networks. One widely used approa…