arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2112.03215cs.LGcs.AIstat.ML
收藏

多尺度特征学习动态:对双下降的见解

Multi-scale Feature Learning Dynamics: Insights for Double Descent

Mila, Université de Montréal(蒙特利尔大学 Mila 研究院);University of California, Riverside(加州大学河滨分校)

Mohammad Pezeshki, Amartya Mitra, Yoshua Bengio, Guillaume Lajoie

摘要:

构建深度学习理论基础的一个关键挑战是神经网络的复杂优化动态,这是由大量网络参数之间的高维相互作用造成的。这种非平凡的动态导致有趣的行为,如“双下降“的现象的泛化误差。这种现象的更常见的研究方面对应于模型方面的双下降,其中测试误差随着模型复杂性的增加而呈现出第二次下降,超出了经典的U形误差曲线。在这项工作中,我们调查的起源较少研究的逐时双下降,其中的测试误差经历了两个非单调的过渡,或下降的训练时间的增加。通过利用统计物理学的工具,我们研究了一个线性师生设置,该设置表现出与深度神经网络类似的逐时双下降。在这种情况下,我们推导出封闭形式的解析表达式的演变泛化误差的训练。我们发现,双下降可以归因于在不同尺度上学习的不同特征:随着快速学习特征过拟合,学习较慢的特征开始拟合,导致测试错误的第二次下降。我们通过数值实验验证了我们的发现,我们的理论准确地预测了经验发现,并与深度神经网络中的观察结果保持一致。

英文摘要:

A key challenge in building theoretical foundations for deep learning is the complex optimization dynamics of neural networks, resulting from the high-dimensional interactions between the large number of network parameters. Such non-trivial dynamics lead to intriguing behaviors such as the phenomenon of "double descent" of the generalization error. The more commonly studied aspect of this phenomenon corresponds to model-wise double descent where the test error exhibits a second descent with increasing model complexity, beyond the classical U-shaped error curve. In this work, we investigate the origins of the less studied epoch-wise double descent in which the test error undergoes two non-monotonous transitions, or descents as the training time increases. By leveraging tools from statistical physics, we study a linear teacher-student setup exhibiting epoch-wise double descent similar to that in deep neural networks. In this setting, we derive closed-form analytical expressions for the evolution of generalization error over training. We find that double descent can be attributed to distinct features being learned at different scales: as fast-learning features overfit, slower-learning features start to fit, resulting in a second descent in test error. We validate our findings through numerical experiments where our theory accurately predicts empirical findings and remains consistent with observations in deep neural networks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑