216 citations · 257 across the 12 of their papers we have counts for
7 papers · 1 filter
Contrastive Losses and Solution Caching for Predict-and-Optimize
Maxime Mulamba, Jayanta Mandi, Michelangelo Diligenti +3
Many decision-making processes involve solving a combinatorial optimization problem with uncertain input that can be estimated from historic data. Recently, problems in this class…
An Analysis of Regularized Approaches for Constrained Machine Learning
Michele Lombardi, Federico Baldo, Andrea Borghesi +1
Regularization-based approaches for injecting constraints in Machine Learning (ML) were introduced to improve a predictive model via expert knowledge. We tackle the issue of findin…
Injecting Domain Knowledge in Neural Networks: a Controlled Experiment on a Constrained Problem
Mattia Silvestri, Michele Lombardi, Michela Milano
Given enough data, Deep Neural Networks (DNNs) are capable of learning complex input-output relations with high accuracy. In several domains, however, data is scarce or expensive t…
Combining Learning and Optimization for Transprecision Computing
Andrea Borghesi, Giuseppe Tagliavini, Michele Lombardi +2
The growing demands of the worldwide IT infrastructure stress the need for reduced power consumption, which is addressed in so-called transprecision computing by improving energy e…
Injective Domain Knowledge in Neural Networks for Transprecision Computing
Andrea Borghesi, Federico Baldo, Michele Lombardi +1
Machine Learning (ML) models are very effective in many learning tasks, due to the capability to extract meaningful information from large data sets. Nevertheless, there are learni…
Teaching the Old Dog New Tricks: Supervised Learning with Constraints
Fabrizio Detassis, Michele Lombardi, Michela Milano
Adding constraint support in Machine Learning has the potential to address outstanding issues in data-driven AI systems, such as safety and fairness. Existing approaches typically…
Lagrangian Duality for Constrained Deep Learning
Ferdinando Fioretto, Pascal Van Hentenryck, Terrence WK Mak +3
This paper explores the potential of Lagrangian duality for learning applications that feature complex constraints. Such constraints arise in many science and engineering domains,…