Regularization Matters: A Nonparametric Perspective on Overparametrized Neural Network
share
Overparametrized neural networks trained by gradient descent (GD) can provably overfit any training data. However, the generalization guarantee may not hold for noisy data. From a nonparametric perspective, this paper studies how well overparametrized neural networks can recover the true target function in the presence of random noises. We establish a lower bound on the L_2 estimation error with respect to the GD iteration, which is away from zero without a delicate choice of early stopping. In turn, through a comprehensive analysis of ℓ_2-regularized GD trajectories, we prove that for overparametrized one-hidden-layer ReLU neural network with the ℓ_2 regularization: (1) the output is close to that of the kernel ridge regression with the corresponding neural tangent kernel; (2) minimax optimal rate of L_2 estimation error is achieved. Numerical experiments confirm our theory and further demonstrate that the ℓ_2 regularization approach improves the training robustness and works for a wider range of neural networks.
READ FULL TEXT