Generalized Invariant Matching Property via LASSO
This work addresses distribution shift problems in machine learning, but it is incremental as it builds upon existing invariant matching property methods.
The paper tackles the challenge of learning under distribution shifts when only the target is intervened, by generalizing the invariant matching property and proposing a robust, computation-efficient algorithm using a Lasso variant.
Learning under distribution shifts is a challenging task. One principled approach is to exploit the invariance principle via the structural causal models. However, the invariance principle is violated when the response is intervened, making it a difficult setting. In a recent work, the invariant matching property has been developed to shed light on this scenario and shows promising performance. In this work, by formulating a high-dimensional problem with intrinsic sparsity, we generalize the invariant matching property for an important setting when only the target is intervened. We propose a more robust and computation-efficient algorithm by leveraging a variant of Lasso, improving upon the existing algorithms.