Showing math.OCShow all
3 papers · 1 filter
math.OC2026
Relaxation-Informed Training of Neural Network Surrogate Models
Calvin Tsay
ReLU neural networks trained as surrogate models can be embedded exactly in mixed-integer linear programs (MILPs), enabling global optimization over the learned function. The tract…
math.OC2026
An Efficient Spatial Branch-and-Bound Algorithm for Global Optimization of Gaussian Process Posterior Mean Functions
Wei-Ting Tang, Akshay Kudva, Calvin Tsay +1
We study the deterministic global optimization of trained Gaussian process posterior mean functions over hyperrectangular domains. Although the posterior mean function has a compac…
math.OC2025
Scaling Mixed-Integer Programming for Certification of Neural Network Controllers Using Bounds Tightening
Philip Sosnin, Calvin Tsay
Neural networks offer a computationally efficient approximation of model predictive control, but they lack guarantees on the resulting controlled system's properties. Formal certif…