Domain Generalization (DG) aims to train models that generalize to unseen target domains but often overfit to domain-specific features, known as undesired correlations. Gradient-based DG methods typically guide gradients in a dominant direction but often inadvertently reinforce spurious correlations. Recent work has employed dropout to regularize overconfident parameters, but has not explicitly adjusted gradient alignment or ensured balanced parameter updates. We propose GENIE (Generalization-ENhancing Iterative Equalizer), a novel optimizer that leverages the One-Step Generalization Ratio (OSGR) to quantify each parameter's contribution to loss reduction and assess gradient alignment. By dynamically equalizing OSGR via a preconditioning factor, GENIE prevents a small subset of parameters from dominating optimization, thereby promoting domain-invariant feature learning. Theoretically, GENIE balances convergence contribution and gradient alignment among parameters, achieving higher OSGR while retaining SGD's convergence rate. Empirically, it outperforms existing optimizers and enhances performance when integrated with various DG and single-DG methods.

翻译：领域泛化旨在训练能泛化到未见目标域的模型，但常过度拟合域特定特征（即非期望的相关性）。基于梯度的领域泛化方法通常将梯度引导至主导方向，却常无意中强化虚假相关性。近期研究采用丢弃法正则化过度自信参数，但未明确调整梯度对齐或确保参数更新均衡。我们提出GENIE（泛化增强迭代均衡器）这一新型优化器，通过一步泛化比率量化各参数对损失降低的贡献并评估梯度对齐。通过前置因子动态均衡OSGR，GENIE能防止少数参数主导优化过程，从而促进域不变特征学习。理论上，GENIE在参数间平衡收敛贡献与梯度对齐，在保持SGD收敛速率的同时实现更高OSGR。实证表明，该优化器优于现有方法，且集成至多种领域泛化及单域泛化方法时可提升性能。