Litcius/Paper detail

Two-Layer Neural Networks with Values in a Banach Space

Yu. M. Korolev

2022SIAM Journal on Mathematical Analysis12 citationsDOIOpen Access PDF

Abstract

We study two-layer neural networks whose domain and range are Banach spaces with separable preduals. In addition, we assume that the image space is equipped with a partial order, i.e., it is a Riesz space. As the nonlinearity we choose the lattice operation of taking the positive part; in case of $\mathbb R^d$-valued neural networks this corresponds to the ReLU activation function. We prove inverse and direct approximation theorems with Monte-Carlo rates for a certain class of functions, extending existing results for the finite-dimensional case. In the second part of the paper we study, from the regularization theory viewpoint, the problem of finding optimal representations of such functions via signed measures on a latent space from a finite number of noisy observations. We discuss regularity conditions known as source conditions and obtain convergence rates in a Bregman distance for the representing measure in the regime when both the noise level goes to zero and the number of samples goes to infinity at appropriate rates.

Topics & Concepts

MathematicsBanach spaceSeparable spaceRegularization (linguistics)Lattice (music)Bregman divergenceNonlinear systemFunction spaceApplied mathematicsArtificial neural networkMathematical analysisSpace (punctuation)Pure mathematicsComputer scienceOperating systemQuantum mechanicsPhysicsMachine learningAcousticsArtificial intelligenceNeural Networks and ApplicationsNumerical methods in inverse problemsModel Reduction and Neural Networks