<ul><li>Domain generalization (DG) aims to create models that perform well on new, unseen domains by addressing distribution shifts.</li><li>Existing methods focusing on aligning domain-level gradients and Hessians for DG are computationally inefficient and lack clear underlying principles.</li><li>This paper introduces the theory of moment alignment for DG, which unifies Invariant Risk Minimization, gradient matching, and Hessian matching approaches.</li><li>The proposed Closed-Form Moment Alignment (CMA) algorithm aligns domain-level gradients and Hessians efficiently, demonstrating superior performance in experiments compared to existing algorithms.</li></ul>

Moment Alignment: Unifying Gradient and Hessian Matching for Domain Generalization

Discover more