N. Benjamin Erichson, Omri Azencot, Alejandro Queiruga, Liam Hodgkinson, Michael W. Mahoney

Research output: Contribution to conferencePaperpeer-review

24 Scopus citations


Viewing recurrent neural networks (RNNs) as continuous-time dynamical systems, we propose a recurrent unit that describes the hidden state's evolution with two parts: a well-understood linear component plus a Lipschitz nonlinearity. This particular functional form facilitates stability analysis of the long-term behavior of the recurrent unit using tools from nonlinear systems theory. In turn, this enables architectural design decisions before experimentation. Sufficient conditions for global stability of the recurrent unit are obtained, motivating a novel scheme for constructing hidden-to-hidden matrices. Our experiments demonstrate that the Lipschitz RNN can outperform existing recurrent units on a range of benchmark tasks, including computer vision, language modeling and speech prediction tasks. Finally, through Hessian-based analysis we demonstrate that our Lipschitz recurrent unit is more robust with respect to input and parameter perturbations as compared to other continuous-time RNNs.

Original languageEnglish
StatePublished - 1 Jan 2021
Event9th International Conference on Learning Representations, ICLR 2021 - Virtual, Online
Duration: 3 May 20217 May 2021


Conference9th International Conference on Learning Representations, ICLR 2021
CityVirtual, Online

ASJC Scopus subject areas

  • Language and Linguistics
  • Computer Science Applications
  • Education
  • Linguistics and Language


Dive into the research topics of 'LIPSCHITZ RECURRENT NEURAL NETWORKS'. Together they form a unique fingerprint.

Cite this