Mean-Field Analysis for Learning Subspace-Sparse Polynomials with Gaussian Input

Ziang Chen, Rong Ge

Keywords: Subspace-sparse polynomial, merged-staircase property, algebraic independence, mean-field analysis, stochastic gradient descent

Abstract: In this work, we study the mean-field flow for learning subspace-sparse polynomials using stochastic gradient descent and two-layer neural networks, where the input distribution is standard Gaussian and the output only depends on the projection of the input onto a low-dimensional subspace. We establish a necessary condition for SGD-learnability, involving both the characteristics of the target function and the expressiveness of the activation function. In addition, we prove that the condition is almost sufficient, in the sense that a condition slightly stronger than the necessary condition can guarantee the exponential decay of the loss functional to zero.

Primary Area: Learning theory

Submission Number: 11764