A Priori Estimates of the Population Risk for Residual Networks
This work provides theoretical guarantees for generalization error in residual networks, which is incremental as it builds on existing norm-based bounds but offers improved estimates.
The authors derived optimal a priori estimates for the population risk of regularized residual networks, introducing a weighted path norm that treats skip connections and nonlinearities differently to regularize paths with more nonlinearities more heavily, achieving bounds comparable to Monte Carlo error rates in high-dimensional settings.
Optimal a priori estimates are derived for the population risk, also known as the generalization error, of a regularized residual network model. An important part of the regularized model is the usage of a new path norm, called the weighted path norm, as the regularization term. The weighted path norm treats the skip connections and the nonlinearities differently so that paths with more nonlinearities are regularized by larger weights. The error estimates are a priori in the sense that the estimates depend only on the target function, not on the parameters obtained in the training process. The estimates are optimal, in a high dimensional setting, in the sense that both the bound for the approximation and estimation errors are comparable to the Monte Carlo error rates. A crucial step in the proof is to establish an optimal bound for the Rademacher complexity of the residual networks. Comparisons are made with existing norm-based generalization error bounds.