Date of Award
5-14-2023
Degree Type
Thesis
Degree Name
Master of Science (MS)
Department
Electrical Engineering and Computer Science
Advisor(s)
Ferdinando Fioretto
Keywords
Computer Science, Constrained Optimization, Machine Learning
Abstract
Achieving fusion of deep learning with combinatorial algorithms promises transformativechanges to AI. Creating an impact in a real-world setting requires AI techniques to span a pipeline from data, to predictive models, to decisions. Aligning these components together requires careful consideration, as having these components trained separately does not account for the end goal of the model. This work surveys general frameworks for melding these components, we focus on the integration of optimization methods with machine learning architectures. We address some challenges and limitations associated with these methods and propose a novel approach to address some of the bottlenecks that arise.
Access
Open Access
Recommended Citation
Farhat, Yehya Marwan, "End-to-End Decision Focused Learning using Learned Solvers" (2023). Theses - ALL. 714.
https://surface.syr.edu/thesis/714
