Constrained-aware Machine Learning

Ferdinando Fioretto
Department of Computer Science, University of Virginia

Time: 2023-10-04, 12:00 - 13:00 ET
Location: Rice 540 and Zoom

Abstract

In recent years, the integration of Machine Learning (ML) with challenging scientific and engineering problems has experienced remarkable growth. In particular, deep learning has proven to be an effective solution for unconstrained problem settings, but it has struggled to perform as well in domains where hard constraints, domain knowledge, or physical principles need to be taken into account. In areas such as power systems, materials science, and fluid dynamics, the data follows well-established physical laws, and ignoring these laws can result in unreliable and ineffective solutions.

In this talk, we will delve into the need for constraint-aware ML. We will present how to integrate key constrained optimization principles within the training process of deep learning models, endowing them with the capability of handling hard constraints and physical principles. The resulting models will bring a new level of accuracy and efficiency to hard decision tasks, which will be showcased on energy and scheduling problems. We will then introduce a powerful integration of constrained optimization as neural network layers, resulting in ML models that are able to enforce structure in the outputs of learned embeddings. This integration will provide ML models with enhanced expressiveness and modeling ability, which will be showcased through the certification fairness in learning to rank tasks and the assembly of high-quality ensemble models. Finally, we will discuss a number of grand challenges that still stand the way to the realization of a potentially transformative technology for both optimization and machine learning.

Bio

Ferdinando Fioretto works on machine learning, optimization, differential privacy, and fairness. His recent work focuses on (1) the integration of constrained optimization and machine learning to enhance the expressive ability of machine learning models and (2) understanding the interplay among privacy, equity, robustness, and performance in machine learning models and decision tasks. He is a recipient of the Amazon Research Award, the NSF CAREER award, the Google Research Scholar Award, the Caspar Bowden PET award, the ISSNAF Mario Gerla Young Investigator Award, the ACP Early Career Researcher Award, the AI*AI Best AI dissertation award, and several best paper awards.