Deep learning methods operate in regimes that defy the traditional statistical mindset. Neural network architectures often contain more parameters than training samples, and are so rich that they can interpolate the observed labels, even if the latter are replaced by pure noise. Despite their huge complexity, the same architectures achieve small generalization error on real data.

中文翻译：

---

随机特征回归的泛化误差：精确渐近和双下降曲线

深度学习方法在违背传统统计思维方式的情况下运行。神经网络架构通常包含比训练样本更多的参数，并且非常丰富以至于它们可以插入观察到的标签，即使后者被纯噪声取代。尽管它们非常复杂，但相同的架构在真实数据上实现了小的泛化误差。