147 citations · 384 across the 17 of their papers we have counts for
3 papers · 2 filters
Optimizing over trained GNNs via symmetry breaking
Shiqiang Zhang, Juan S. Campos, Christian Feldmann +5
Optimization over trained machine learning models has applications including: verification, minimizing neural acquisition functions, and integrating a trained surrogate into a larg…
When Deep Learning Meets Polyhedral Theory: A Survey
Joey Huchette, Gonzalo Muñoz, Thiago Serra +1
In the past decade, deep learning became the prevalent methodology for predictive modeling thanks to the remarkable accuracy of deep neural networks in tasks such as computer visio…
Model-based feature selection for neural networks: A mixed-integer programming approach
Shudian Zhao, Calvin Tsay, Jan Kronqvist
In this work, we develop a novel input feature selection framework for ReLU-based deep neural networks (DNNs), which builds upon a mixed-integer optimization approach. While the me…