IE Seminar: “Reliable Data-driven Decision Making”, Bahar Taşkesen, 1:30PM January 5 (EN)

Speaker: Bahar Taşkesen (EPFL)
Title: Reliable Data-driven Decision Making

Place: EA-409
Date: January 5, 2024 (Friday)
Time: 13:30 – 14:30

We are witnessing a remarkable surge in data availability across various domains, including medicine, education, policy-making, marketing, civics, and many more. This data deluge has created opportunities for developing intelligent systems capable of implementing highly precise and personalized decisions at unprecedented scales. Simultaneously, the application of machine learning in areas such as criminal justice and health care, which carry significant consequences for individuals, has prompted inquiries into the appropriate design of these systems to ensure alignment with our societal values. In this talk, I will use optimal transport (OT), which seeks the most efficient way of morphing one distribution into another one, as a tool to model and audit data-driven decision-making systems. First, we will see how OT gives rise to a rich class of data-driven distributionally robust optimization (DRO) models, which study worst-case risk minimization problems under distributional ambiguity. We will then shift our focus to an auditing perspective and see how OT can naturally facilitate a statistical test for the algorithmic fairness of pre-trained machine learning models. A significant yet unexplored aspect of OT is its computational complexity. Addressing this gap, we will see the computational complexity of generic OT problems. Later, we will see that even though generic OT problems are computationally hard, we can develop reliable data-driven decision-making models that are tractable in static and dynamic environments and would bring out-of-sample guarantees. In particular, we will see the optimality of linear policies in OT-based robust linear-quadratic control problems with imperfect state observations, and we will show that these policies can be computed efficiently using dynamic programming, Kalman filtering, and automatic differentiation.

Bahar Taşkesen is a 5th-year Ph.D. candidate in the Risk Analytics and Optimization Lab at the École Polytechnique Fédérale de Lausanne (EPFL) in Switzerland, under the supervision of Daniel Kuhn. She obtained her Bachelor’s degree in Electrical and Electronics Engineering from Middle East Technical University in Ankara, Turkey, in 2018. Her research interests center around data-driven decision-making under uncertainty, large-scale stochastic optimization, and statistical inference. She is particularly interested in exploring algorithmic fairness and robustness and their applications in operations management, control, and machine learning. Her work has implications for the development and deployment of responsible AI systems.