Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization
This addresses the challenge of out-of-distribution generalization for machine learning applications, representing an incremental advance over existing methods.
The paper tackles the problem of learning robust models that generalize under distribution shifts by introducing Fishr, a regularization method that enforces domain invariance in gradient variances, and it improves state-of-the-art results on the DomainBed benchmark.
Learning robust models that generalize well under changes in the data distribution is critical for real-world applications. To this end, there has been a growing surge of interest to learn simultaneously from multiple training domains - while enforcing different types of invariance across those domains. Yet, all existing approaches fail to show systematic benefits under controlled evaluation protocols. In this paper, we introduce a new regularization - named Fishr - that enforces domain invariance in the space of the gradients of the loss: specifically, the domain-level variances of gradients are matched across training domains. Our approach is based on the close relations between the gradient covariance, the Fisher Information and the Hessian of the loss: in particular, we show that Fishr eventually aligns the domain-level loss landscapes locally around the final weights. Extensive experiments demonstrate the effectiveness of Fishr for out-of-distribution generalization. Notably, Fishr improves the state of the art on the DomainBed benchmark and performs consistently better than Empirical Risk Minimization. Our code is available at https://github.com/alexrame/fishr.