Lipschitz Recurrent Neural Networks
From MaRDI portal
Publication:6343423
arXiv2006.12070MaRDI QIDQ6343423
Author name not available (Why is that?)
Publication date: 22 June 2020
Abstract: 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.
Has companion code repository: https://github.com/erichson/LipschitzRNN
This page was built for publication: Lipschitz Recurrent Neural Networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6343423)
