Loading Events

« All Events

  • This event has passed.

ESE Thesis Defense: “Constrained Learning and Inference”

September 22 at 9:00 AM - 10:30 AM

Learning is a core component of the information processing and autonomous systems upon which we increasingly rely on to select job applicants, analyze medical data, and drive cars. As these systems become ubiquitous, so does the need to curtail their behavior. Left untethered, they are susceptible to tampering (adversarial examples) and prone to prejudiced and unsafe actions. Currently, this is done by either constructing models that embed the desired properties or tuning the training objective so as to promote them. Yet, these approaches are often tailored to specific problems, are hard to transfer between models, and involve time consuming trial-and-error procedures that are impractical even for the current scale and complexity of modern machine learning systems. In this defense, I develop the theoretical underpinnings of constrained learning to understand how requirements affect statistical learning and enable behaviors to be directly and systematically designed. To do so, I will derive a generalization theory for constrained learning based on the probably approximately correct (PAC) learning framework. In particular, I will show that imposing requirements does not make a learning problem harder in the sense that any PAC learnable class is also PAC constrained learnable using a constrained counterpart of the empirical risk minimization (ERM) rule. For typical parametrized models, however, this learner involves solving a non-convex constrained optimization program for which even obtaining a feasible solution may be hard. To overcome this issue, we prove that under mild conditions the empirical dual problem of constrained learning is also a PAC constrained learner. Hence, constrained learning problems can be solved by solving only unconstrained ones, leading to a practical constrained learning algorithm. We illustrate how constrained learning can address problems in fair and robust classification.

Luiz F. O. Chamon

Ph.D. Candidate

Luiz Chamon received the B.Sc. and M.Sc. degree in electrical engineering from the University of São Paulo, São Paulo, Brazil, in 2011 and 2015. In 2009, he was an undergraduate exchange student at the Masters in Acoustics of the École Centrale de Lyon, Lyon, France. He is currently working toward the Ph.D. degree in electrical and systems engineering at the University of Pennsylvania (Penn), Philadelphia. In 2009, he was an Assistant Instructor and Consultant on nondestructive testing at INSACAST Formation Continue. From 2010 to 2014, he worked as a Signal Processing and Statistical Consultant on a project with EMBRAER. He received both the best student paper and the best paper award at ICASSP 2020. His research interests include optimization, signal processing, machine learning, statistics, and control.

George J. Pappas, Penn (chair)
Alejandro Ribeiro, Penn (advisor)
Yonina C. Eldar, Weissmann
Hamed Hassani, Penn
Nikolai Matni, Penn


Zoom – Email ESE for Link jbatter@seas.upenn.edu


Electrical and Systems Engineering