# Contracting Neural Networks: Sharp LMI Conditions with Applications to Integral Control and Deep Learning

Source: [Contracting Neural Networks: Sharp LMI Conditions with Applications to Integral Control and Deep Learning](<https://www.sota2.com/research/paper/69cdf7ec0636e5bf4afcc94a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-03T05:00:04.568Z

Authors: Anand Gokhale, Anton V. Proskurnikov, Yu Kawano, Francesco Bullo

Published: 2026-03-31T18:27:33.000Z

## Abstract

This paper studies contractivity of firing-rate and Hopfield recurrent neural networks. We derive sharp LMI conditions on the synaptic matrices that characterize contractivity of both architectures, for activation functions that are either non-expansive or monotone non-expansive, in both continuous and discrete time. We establish structural relationships among these conditions, including connections to Schur diagonal stability and the recovery of optimal contraction rates for symmetric synaptic matrices. We demonstrate the utility of these results through two applications. First, we develop an LMI-based design procedure for low-gain integral controllers enabling reference tracking in contracting firing rate networks. Second, we provide an exact parameterization of weight matrices that guarantee contraction and use it to improve the expressivity of Implicit Neural Networks, achieving competitive performance on image classification benchmarks with fewer parameters.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.00119>)

[PDF](<https://arxiv.org/pdf/2604.00119.pdf>)