Transportable Representations for Out-of-distribution Generalization
Amirkasra Jalaldoust · Elias Bareinboim
Abstract
Building on the theory of causal transportability (Bareinboim & Pearl), we define in this paper the notion of ``transportable representations," and show that the out-of-distribution generalization risk of classifiers defined based on these representations can be bounded, considering that graphical assumptions about the underlying system are provided.
Chat is not available.
Successful Page Load