Eigenvalue spectral properties of sparse random matrices obeying Dale's law

TL;DR

This paper extends classical eigenvalue spectral results to sparse neural networks obeying Dale's law, revealing how sparsity and E/I statistics influence network stability and eigenvalue distribution.

Contribution

It provides explicit formulas showing the interaction of sparsity with E/I population statistics on the eigenspectrum, including the presence of eigenvalue outliers and density changes.

Findings

Eigenspectral outlier scales linearly with sparsity

Eigenspectral radius depends nonlinearly on E/I statistics and sparsity

Local eigenvalue outliers can be controlled or persist depending on network balance

Abstract

This paper examines the relationship between sparse random network architectures and neural network stability by examining the eigenvalue spectral distribution. Specifically, we generalise classical eigenspectral results to sparse connectivity matrices obeying Dale's law: neurons function as either excitatory (E) or inhibitory (I). By defining sparsity as the probability that a neutron is connected to another neutron, we give explicit formulae that shows how sparsity interacts with the E/I population statistics to scale key features of the eigenspectrum, in both the balanced and unbalanced cases. Our results show that the eigenspectral outlier is linearly scaled by sparsity, but the eigenspectral radius and density now depend on a nonlinear interaction between sparsity, the E/I population means and variances. Contrary to previous results, we demonstrate that a non-uniform eigenspectral density results if any of the E/I population statistics differ, not just the E/I population variances. We also find that 'local' eigenvalue-outliers are present for sparse random matrices obeying Dale's law, and demonstrate that these eigenvalues can be controlled by a modified zero row-sum constraint for the balanced case, however, they persist in the unbalanced case. We examine all levels of connection (sparsity), and distributed E/I population weights, to describe a general class of sparse connectivity structures which unifies all the previous results as special cases of our framework. Sparsity and Dale's law are both fundamental anatomical properties of biological neural networks. We generalise their combined effects on the eigenspectrum of random neural networks, thereby gaining insight into network stability, state transitions and the structure-function relationship.