Timezone: »

Optimization and Generalization of Shallow Neural Networks with Quadratic Activation Functions
Stefano Sarao Mannelli · Eric Vanden-Eijnden · Lenka Zdeborová

Thu Dec 10 09:00 AM -- 11:00 AM (PST) @ Poster Session 5 #1561

We study the dynamics of optimization and the generalization properties of one-hidden layer neural networks with quadratic activation function in the overparametrized regime where the layer width m is larger than the input dimension d.

We consider a teacher-student scenario where the teacher has the same structure as the student with a hidden layer of smaller width m*<=m.

We describe how the empirical loss landscape is affected by the number n of data samples and the width m* of the teacher network. In particular we determine how the probability that there be no spurious minima on the empirical loss depends on n, d, and m*, thereby establishing conditions under which the neural network can in principle recover the teacher.

We also show that under the same conditions gradient descent dynamics on the empirical loss converges and leads to small generalization error, i.e. it enables recovery in practice.

Finally we characterize the time-convergence rate of gradient descent in the limit of a large number of samples.

These results are confirmed by numerical experiments.

Author Information

Stefano Sarao Mannelli (university of Oxford)
Eric Vanden-Eijnden (New York University)
Lenka Zdeborová (EPFL)

More from the Same Authors