Statistical Mechanics of Deep Linear Neural Networks: The Back-Propagating Kernel Renormalization
This work provides a foundational theoretical framework for understanding learning in deep neural networks, which is crucial for researchers in statistical mechanics and machine learning.
This paper investigates Deep Linear Neural Networks (DLNNs) using statistical mechanics to understand training and generalization. It introduces the Back-Propagating Kernel Renormalization (BPKR) method, which allows exact calculation of network properties like generalization error, the impact of width, depth, training set size, and regularization, and shows that these predictions largely hold for ReLU networks in numerical simulations.
The success of deep learning in many real-world tasks has triggered an intense effort to understand the power and limitations of deep learning in the training and generalization of complex tasks, so far with limited progress. In this work, we study the statistical mechanics of learning in Deep Linear Neural Networks (DLNNs) in which the input-output function of an individual unit is linear. Despite the linearity of the units, learning in DLNNs is nonlinear, hence studying its properties reveals some of the features of nonlinear Deep Neural Networks (DNNs). Importantly, we solve exactly the network properties following supervised learning using an equilibrium Gibbs distribution in the weight space. To do this, we introduce the Back-Propagating Kernel Renormalization (BPKR), which allows for the incremental integration of the network weights starting from the network output layer and progressing backward until the first layer's weights are integrated out. This procedure allows us to evaluate important network properties, such as its generalization error, the role of network width and depth, the impact of the size of the training set, and the effects of weight regularization and learning stochasticity. BPKR does not assume specific statistics of the input or the task's output. Furthermore, by performing partial integration of the layers, the BPKR allows us to compute the properties of the neural representations across the different hidden layers. We have proposed an extension of the BPKR to nonlinear DNNs with ReLU. Surprisingly, our numerical simulations reveal that despite the nonlinearity, the predictions of our theory are largely shared by ReLU networks in a wide regime of parameters. Our work is the first exact statistical mechanical study of learning in a family of DNNs, and the first successful theory of learning through successive integration of DoFs in the learned weight space.