It’s all in the mix: Wasserstein machine learning with mixed features
August 30, 2024 10:00 AM Singapore (Registration starts at 9:50 AM)
Abstract
A key challenge in data-driven decision-making is the presence of estimation errors in the prediction models, which tend to be amplified by the subsequent optimization model — a phenomenon that is often referred to as the Optimizer’s Curse. A contemporary approach to combat such estimation errors is offered by distributionally robust problem formulations that consider all data-generating distributions close to the empirical distribution derived from historical samples, where ‘closeness’ is determined by the Wasserstein distance. While those techniques show significant promise in problems where all input features are continuous, they scale exponentially when categorical features are present. This work demonstrates that such mixed-feature problems can indeed be solved in polynomial time. We present a practically efficient algorithm to solve mixed-feature problems and compare our method against alternative techniques.
PAPER: https://arxiv.org/abs/2312.12230
About the Speaker
Aras is a final-year doctoral candidate at Imperial College Business School, advised by Wolfram Wiesemann as a member of the Models and Algorithms for Decision-Making under Uncertainty research group. He is affiliated with the Computational Optimization Group and the Data Science Institute of Imperial College London. Aras has recently completed a PhD placement at The Alan Turing Institute and a PhD Associate Internship at JP Morgan AI Research.
Aras’s research interests are the theory of data-driven decision-making under uncertainty and its applications in machine learning, privacy, and fairness. In his recent works, he has been working on designing optimal privacy mechanisms, developing efficient algorithms for robust machine learning, and approximating hard decision-making problems via robust optimization.
For more information about the ESD Seminar, please email esd_invite@sutd.edu.sg