UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Proliferation of non-linear excitations in the piecewise-linear perceptron

Sclocchi, Antonio; Urbani, Pierfrancesco; (2021) Proliferation of non-linear excitations in the piecewise-linear perceptron. SciPost Physics , 10 (1) , Article 013. 10.21468/scipostphys.10.1.013. Green open access

[thumbnail of Sclocchi_SciPostPhys_10_1_013.pdf]
Preview
Text
Sclocchi_SciPostPhys_10_1_013.pdf

Download (551kB) | Preview

Abstract

We investigate the properties of local minima of the energy landscape of a continuous non-convex optimization problem, the spherical perceptron with piecewise linear cost function and show that they are critical, marginally stable and displaying a set of pseudogaps, singularities and non-linear excitations whose properties appear to be in the same universality class of jammed packings of hard spheres. The piecewise linear perceptron problem appears as an evolution of the purely linear perceptron optimization problem that has been recently investigated in [1]. Its cost function contains two non-analytic points where the derivative has a jump. Correspondingly, in the non-convex/glassy phase, these two points give rise to four pseudogaps in the force distribution and this induces four power laws in the gap distribution as well. In addition one can define an extended notion of isostaticity and show that local minima appear again to be isostatic in this phase. We believe that our results generalize naturally to more complex cases with a proliferation of non-linear excitations as the number of non-analytic points in the cost function is increased.

Type: Article
Title: Proliferation of non-linear excitations in the piecewise-linear perceptron
Open access status: An open access version is available from UCL Discovery
DOI: 10.21468/scipostphys.10.1.013
Publisher version: https://doi.org/10.21468/scipostphys.10.1.013
Language: English
Additional information: Copyright A. Sclocchi and P. Urbani. This work is licensed under the Creative Commons Attribution 4.0 International License. Published by the SciPost Foundation.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Life Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Life Sciences > Gatsby Computational Neurosci Unit
URI: https://discovery.ucl.ac.uk/id/eprint/10206013
Downloads since deposit
0Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item