Out-of-Variable Generalization for Discriminative Models

The ability of an agent to do well in new environments is a critical aspect of intelligence. In machine learning, this ability is known as textitstrong or textitout-of-distribution generalization. However, merely considering differences in data distributions is inadequate for fully capturing differences between learning environments. In the present paper, we investigate textitout-of-variable generalization, which pertains to an agent's generalization capabilities concerning environments with variables that were never jointly observed before. This skill closely reflects the process of animate learning: we, too, explore Nature by probing, observing, and measuring textitsubsets of variables at any given time. Mathematically, textitout-of-variable generalization requires the efficient re-use of past marginal information, i.e., information over subsets of previously observed variables. We study this problem, focusing on prediction tasks across environments that contain overlapping, yet distinct, sets of causes. We show that after fitting a classifier, the residual distribution in one environment reveals the partial derivative of the true generating function with respect to the unobserved causal parent in that environment. We leverage this information and propose a method that exhibits non-trivial out-of-variable generalization performance when facing an overlapping, yet distinct, set of causal predictors.