Generalisation dynamics of online learning in over-parameterised neural networks
This provides theoretical insights into generalization dynamics for researchers in machine learning, though it is incremental as it builds on existing teacher-student models.
The paper tackles the problem of understanding generalization in over-parameterized neural networks by analyzing a teacher-student setup, showing that generalization error increases linearly with network size under specific conditions.
Deep neural networks achieve stellar generalisation on a variety of problems, despite often being large enough to easily fit all their training data. Here we study the generalisation dynamics of two-layer neural networks in a teacher-student setup, where one network, the student, is trained using stochastic gradient descent (SGD) on data generated by another network, called the teacher. We show how for this problem, the dynamics of SGD are captured by a set of differential equations. In particular, we demonstrate analytically that the generalisation error of the student increases linearly with the network size, with other relevant parameters held constant. Our results indicate that achieving good generalisation in neural networks depends on the interplay of at least the algorithm, its learning rate, the model architecture, and the data set.