By reducing the curvature of the loss surface in the parameter space,
Sharpness-aware minimization (SAM) yields widespread robustness improvement
under domain transfer. Instead of focusing on parameters, however, this work
considers the transferability of representations as the optimization target for
out-of-domain generalization in a fine-tuning setup. To encourage the retention
of transferable representations, we consider trust region-based fine-tuning
methods, which exploit task-specific skills without forgetting task-agnostic
representations from pre-training. We unify parameter- and representation-space
smoothing approaches by using trust region bounds to inform SAM-style
regularizers on both of these optimization surfaces. We propose Trust Region
Aware Minimization (TRAM), a fine-tuning algorithm that optimizes for flat
minima and smooth, informative representations without forgetting pre-trained
structure. We find that TRAM outperforms both sharpness-aware and trust
region-based optimization methods on cross-domain language modeling and
cross-lingual transfer, where robustness to domain transfer and representation
generality are critical for success. TRAM establishes a new standard in
training generalizable models with minimal additional computation.

通过降低参数空间中损失曲面的曲率，锐度感知最小化（SAM）在域转换下实现了广泛的稳健性改进。本研究不关注参数，而是将表示的可转移性作为优化目标，在微调设置中进行跨域泛化的优化。我们考虑基于信任区域的微调方法，以鼓励保持可转移表示，并通过使用信任区域边界在两个优化表面上通知 SAM 风格的正则化方法来统一参数和表示空间平滑方法。我们提出了一种称为 Trust Region Aware Minimization（TRAM）的微调算法，该算法在不忘记预训练结构的情况下，优化平坦的最小值和平滑的信息表示。我们发现，TRAM 在跨领域语言建模和跨语言转移方面胜过锐度感知和基于信任区域的优化方法，在这些任务中，域转换的健壮性和表示的普适性对于成功至关重要。TRAM 为使用最少额外计算训练可推广模型确立了一个新的标准。