Event Actions
Machine Learning for Fair and Risk-Aware Optimization
Abstract:
This paper explores the intergration of Machine Learning (ML) and Optimization, focusing on two frameworks: Learning to Optimize (LTO) and Predict-Then-Optimize (PtO). These approaches leverage the strengths of both domains to enhance real-world problem-solving capabilities. The LTO framework utilizes ML models, particularly neural networks, to accelerate the solution of constrained optimization problems. We demonstrate its application in power systems, specifically for the AC Optimal Power Flow problem, where our approach significantly reduces computational costs while maintaining high accuracy. The PtO framework integrates ML and optimization by incorporating the optimization layer directly into the ML training process. Our contributions in this area focus on multi-objective optimization applications, including learning-to-rank, court scheduling, and portfolio management. By integrating optimization layers into ML models, we address challenges such as fairness and risk management, leading to more robust and effective decision-making processes. This research highlights the potential of combining ML and optimization techniques to tackle complex real-world problems more efficiently and accurately.
Committee:
- Anil Vullikanti, Committee Chair (CS, Biocomplexity/SEAS/UVA)
- Ferdinando Fioretto, Advisor (CS/SEAS/UVA)
- Jundong Li (CS, ECE/SEAS, SDS/UVA)
- Henry A. Kautz (CS/SEAS/UVA)
- Max R. Bigg (SoB/UVA)