2 papers
math.OC2026
Optimization over Trained (and Sparse) Neural Networks: A Surrogate within a Surrogate
Hung Pham, Aiden Ren, Ibrahim Tahir +2
In constraint learning, we use a neural network as a surrogate for part of the constraints or of the objective function of an optimization model. However, the tractability of the r…
math.FA2024
Constructing non-AMNM weighted convolution algebras for every semilattice of infinite breadth
Yemon Choi, Mahya Ghandehari, Hung Le Pham
The AMNM property for commutative Banach algebras is a form of Ulam stability for multiplicative linear functionals. We show that on any semilattice of infinite breadth, one may co…