Framing RNN as a kernel method: A neural ODE approach

Abstract

Building on the interpretation of a recurrent neural network (RNN) as a continuous-time neural differential equation, we show, under appropriate conditions, that the solution of a RNN can be viewed as a linear function of a specific feature set of the input sequence, known as the signature. This connection allows us to frame a RNN as a kernel method in a suitable reproducing kernel Hilbert space. As a consequence, we obtain theoretical guarantees on generalization and stability for a large class of recurrent networks. Our results are illustrated on simulated datasets.

33 pages, 7 figures, accepted for an oral presentation at NeurIPS 2021

References in corpus (5)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Natural Language Processing (almost) from Scratch
• AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networks
• Rough paths, Signatures and the modelling of functions on streams
• POPQORN: Quantifying Robustness of Recurrent Neural Networks