Year: 2020
Type: preprint
Abstract: The marriage of recurrent neural networks and neural ordinary differential networks (ODE-RNN) is effective in modeling irregularly-observed sequences. While ODE produces the smooth hidden states between observation intervals, the RNN will trigger a hidden state jump when a new observation arrives, thus cause the interpolation discontinuity problem. To address this issue, we propose the cubic spline smoothing compensation, which is a stand-alone module upon either the output or the hidden state of ODE-RNN and can be trained end-to-end. We derive its analytical solution and provide its theoretical interpolation error bound. Extensive experiments indicate its merits over both ODE-RNN and cubic spline interpolation.
Source: arXiv (Cornell University)
Authors: Shi, Jing, Bi, Jing, Liu, Yingru, Xu, Chenliang
Institutions: University of Rochester, Stony Brook University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3090034874