用梯度与权重的对齐程度，实时判断模型是否过拟合。
Gradient-Weight Alignment as a Train-Time Proxy for Generalization in Classification Tasks
- 通过计算每样本梯度与模型权重的对齐度，衡量学习一致性。
- 对齐度下降时，模型泛化能力变差，可提前停止训练。
- 无需验证集，能识别关键训练样本，适合模型调试与分析。
在监督分类任务中，我们研究训练数据与模型权重之间的交互是否能生成一个既能追踪训练过程中的泛化性能，又能归因于单个训练样本的鲁棒验证指标。本文提出梯度-权重对齐（Gradient-Weight Alignment, GWA），量化每个样本梯度与模型权重间的协同程度。实验表明，有效学习对应良好的对齐，而对齐度下降预示泛化性能恶化。GWA 可在训练过程中高效计算，反映样本级贡献与整体学习动态。大量实验证明，它能准确预测最优早停时机，支持合理模型比较，并识别关键训练样本，实现完全依赖训练数据的模型分析，无需验证集。
原文摘要 · Abstract (English)
Robust validation metrics remain essential in contemporary deep learning, not only to detect overfitting and poor generalization, but also to monitor training dynamics. In the supervised classification setting, we investigate whether interactions between training data and model weights can yield such a metric that both tracks generalization during training and attributes performance to individual training samples. We introduce Gradient-Weight Alignment (GWA), quantifying the coherence between per-sample gradients and model weights. We show that effective learning corresponds to coherent alignment, while misalignment indicates deteriorating generalization. GWA is efficiently computable during training and reflects both sample-specific contributions and dataset-wide learning dynamics. Extensive experiments show that GWA accurately predicts optimal early stopping, enables principled model comparisons, and identifies influential training samples, providing a validation-set-free approach for model analysis directly from the training data.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。