Implicit bias of gradient descent for mean squared error regression with wide neural networks

06/12/2020 ∙ by Hui Jin, et al. ∙ 23

We investigate gradient descent training of wide neural networks and the corresponding implicit bias in function space. Focusing on 1D regression, we show that the solution of training a width-n shallow ReLU network is within n^- 1/2 of the function which fits the training data and whose difference from initialization has smallest 2-norm of the second derivative weighted by 1/ζ. The curvature penalty function 1/ζ is expressed in terms of the probability distribution that is utilized to initialize the network parameters, and we compute it explicitly for various common initialization procedures. For instance, asymmetric initialization with a uniform distribution yields a constant curvature penalty, and thence the solution function is the natural cubic spline interpolation of the training data. The statement generalizes to the training trajectories, which in turn are captured by trajectories of spatially adaptive smoothing splines with decreasing regularization strength.



There are no comments yet.


page 17

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.