Adversarially Robust Learning: Identification, Estimation, and Uncertainty Quantification
Empirical risk minimization may lead to poor prediction performance when the target distribution differs from the source populations. This talk discusses leveraging data from multiple sources and constructing more generalizable and transportable prediction models. We introduce an adversarially robust prediction model to optimize a worst-case reward concerning a class of target distributions and show that our introduced model is a weighted average of the source populations’ conditional outcome models. We leverage this identification result to robustify arbitrary machine learning algorithms, including, for example, high-dimensional regression, random forests, and neural networks. In our adversarial learning framework, we propose a novel sampling method to quantify the uncertainty of the adversarial robust prediction model. Moreover, we introduce guided adversarially robust transfer learning (GART) that uses a small amount of target domain data to guide adversarial learning. We show that GART achieves a faster convergence rate than the model fitted with the target data. Our comprehensive simulation studies suggest that GART can substantially outperform existing transfer learning methods, attaining higher robustness and accuracy.
Date: 14 June 2024, 14:15 (Friday, 8th week, Trinity 2024)
Venue: Manor Road Building, Manor Road OX1 3UQ
Venue Details: Seminar Room C or https://zoom.us/j/93054414699?pwd=YnpYaDhncCtWdGN0MUdJQ1NmRTlGZz09
Speaker: Zijian Guo (Rutgers University)
Organising department: Department of Economics
Part of: Nuffield Econometrics Seminar
Booking required?: Not required
Audience: Members of the University only
Editor: Edward Clark