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 …

Training neural networks (NNs) using combinatorial optimization solvers has gained
attention in recent years. In low-data settings, the use of state-of-the-art mixed integer linear …

The use of Mixed-Integer Linear Programming (MILP) models to represent neural networks
with Rectified Linear Unit (ReLU) activations has become increasingly widespread in the …

Besides training, mathematical optimization is also used in deep learning to model and
solve formulations over trained neural networks for purposes such as verification …

The non-convex nature of trained neural networks has created significant obstacles in their
incorporation into optimization models. Considering the wide array of applications that this …

We propose a fast method for exactly enumerating a large number of all cost-bounded
solutions for combinatorial problems using Zero-suppressed Binary Decision Diagrams …

This thesis explores innovative methodologies in two distinct areas of Applied Mathematics:
Mathematical Modelling in Biosciences and Discrete Optimization. The work is structured …