Modern machine learning models with a large number of parameters often generalize well despite perfectly interpolating noisy training data - a phenomenon known as benign overfitting. A foundational explanation for this in linear classification was recently provided by Hashimoto et al. (2025). However, this analysis was limited to the setting of "homogeneous" models, which lack a bias (intercept) term - a standard component in practice. This work directly extends Hashimoto et al.'s results to the more realistic inhomogeneous case, which incorporates a bias term. Our analysis proves that benign overfitting persists in these more complex models. We find that the presence of the bias term introduces new constraints on the data's covariance structure required for generalization, an effect that is particularly pronounced when label noise is present. However, we show that in the isotropic case, these new constraints are dominated by the requirements inherited from the homogeneous model. This work provides a more complete picture of benign overfitting, revealing the non-trivial impact of the bias term on the conditions required for good generalization.
翻译:现代机器学习模型通常具有大量参数,尽管能够完美插值含噪声的训练数据,却仍表现出良好的泛化能力——这一现象被称为良性过拟合。Hashimoto等人(2025年)最近为线性分类中的这一现象提供了基础性解释。然而,该分析仅限于“齐次”模型(即不含偏置项或截距项)的场景,而偏置项在实践中是标准组件。本研究直接将Hashimoto等人的结果推广至更贴近实际的非齐次情形,即包含偏置项的模型。我们的分析证明,良性过拟合在这些更复杂的模型中依然存在。研究发现,偏置项的引入对数据协方差结构提出了新的约束条件以确保泛化能力,这一效应在存在标签噪声时尤为显著。然而,我们证明在各向同性情况下,这些新约束条件被齐次模型继承的要求所主导。本工作为良性过拟合提供了更完整的理论图景,揭示了偏置项对良好泛化所需条件的非平凡影响。