|Domain Generalization with Adversarially Robust Learning: Identiﬁcation, Estimation, and Uncertainty Quantification
|2:00 pm - 3:00 pm
|LPN LT in Y. C. Liang Hall
|Professor Zijian Guo
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.