On the Role of Depth in the Expressivity of RNNs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lizaire, Maude, Rizvi-Martel, Michael, Dupuis, Éric, Rabusseau, Guillaume
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915909923241984
author Lizaire, Maude
Rizvi-Martel, Michael
Dupuis, Éric
Rabusseau, Guillaume
author_facet Lizaire, Maude
Rizvi-Martel, Michael
Dupuis, Éric
Rabusseau, Guillaume
contents The benefits of depth in feedforward neural networks are well known: composing multiple layers of linear transformations with nonlinear activations enables complex computations. While similar effects are expected in recurrent neural networks (RNNs), it remains unclear how depth interacts with recurrence to shape expressive power. Here, we formally show that depth increases RNNs' memory capacity efficiently with respect to the number of parameters, thus enhancing expressivity both by enabling more complex input transformations and improving the retention of past information. We broaden our analysis to 2RNNs, a generalization of RNNs with multiplicative interactions between inputs and hidden states. Unlike RNNs, which remain linear without nonlinear activations, 2RNNs perform polynomial transformations whose maximal degree grows with depth. We further show that multiplicative interactions cannot, in general, be replaced by layerwise nonlinearities. Finally, we validate these insights empirically on synthetic and real-world tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2604_02201
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle On the Role of Depth in the Expressivity of RNNs
Lizaire, Maude
Rizvi-Martel, Michael
Dupuis, Éric
Rabusseau, Guillaume
Machine Learning
The benefits of depth in feedforward neural networks are well known: composing multiple layers of linear transformations with nonlinear activations enables complex computations. While similar effects are expected in recurrent neural networks (RNNs), it remains unclear how depth interacts with recurrence to shape expressive power. Here, we formally show that depth increases RNNs' memory capacity efficiently with respect to the number of parameters, thus enhancing expressivity both by enabling more complex input transformations and improving the retention of past information. We broaden our analysis to 2RNNs, a generalization of RNNs with multiplicative interactions between inputs and hidden states. Unlike RNNs, which remain linear without nonlinear activations, 2RNNs perform polynomial transformations whose maximal degree grows with depth. We further show that multiplicative interactions cannot, in general, be replaced by layerwise nonlinearities. Finally, we validate these insights empirically on synthetic and real-world tasks.
title On the Role of Depth in the Expressivity of RNNs
topic Machine Learning
url https://arxiv.org/abs/2604.02201