Searcharxiv⌕ Search

arXiv subjects

Ming-Xi Wang

Publications and source records attributed to Ming-Xi Wang.

4 recordsLinked to original sources
arXiv2021

Approximation capabilities of neural networks on unbounded domains

In this paper, we prove that a shallow neural network with a monotone sigmoid, ReLU, ELU, Softplus, or LeakyReLU activation function can arbitrarily well approximate any L^p(p>=2) integrable functions defined on R*[0,1]^n. We also prove that a shallow neural network with a sigmoid, ReLU, ELU, Softplus, or LeakyReLU activation function expresses no nonzero integrable function defined on the Euclidean plane. Together with a recent result that the deep ReLU network can arbitrarily well approximate any integrable function on Euclidean spaces, we provide a new perspective on the advantage of multiple hidden layers in the context of ReLU networks. Lastly, we prove that the ReLU network with depth 3 is a universal approximator in L^p(R^n).

cs.LG↗
arXiv2021

The option pricing model based on time values: an application of the universal approximation theory on unbounded domains

We propose a time value related decision function to treat a classical option pricing problem raised by Hutchinson-Lo-Poggio. In numerical experiments, the new decision function significantly improves the original model of Hutchinson-Lo-Poggio with faster convergence and better generalization performance. By proving a novel universal approximation theorem, we show that our decision function rather than Hutchinson-Lo-Poggio's can be approximated on the entire domain of definition by neural networks. Thus the experimental results are partially explained by the representation properties of networks.

q-fin.CP↗
arXiv2014

Isogeny orbits in a family of abelian varieties

We prove that if a curve of a non-isotrivial family of abelian varieties over a curve contains infinitely many isogeny orbits of a finitely generated subgroup of a simple abelian variety then it is special.

math.NT↗