Steven Low — accepted AI-conference papers

2023

Ensuring DNN Solution Feasibility for Optimization Problems with Linear Constraints

Tianyu Zhao, Xiang Pan, Minghua Chen, Steven Low

ICLR 2023top-25%

We propose preventive learning as the first framework to guarantee Deep Neural Network (DNN) solution feasibility for optimization problems with linear constraints without post-processing, upon satisfying a mild condition on constraint calibration. Without loss of generality, we focus on problems wi…

Cited by 13 Source ↗PDF ↗Scholar ↗

2023

Low Complexity Homeomorphic Projection to Ensure Neural-Network Solution Feasibility for Optimization over (Non-)Convex Set

Enming Liang, Minghua Chen, Steven Low

ICML 2023poster

There has been growing interest in employing neural network (NN) to directly solve constrained optimization problems with low run-time complexity. However, it is non-trivial to ensure NN solutions strictly satisfying problem constraints due to inherent NN prediction errors. Existing feasibility-ensu…

Cited by 15 Source ↗PDF ↗Scholar ↗