论文标题
对于不规则采样序列的立方样条平滑补偿
Cubic Spline Smoothing Compensation for Irregularly Sampled Sequences
论文作者
论文摘要
复发性神经网络和神经普通差分网络（ODE-RNN）的结合在对不规则观察到的序列进行建模方面有效。尽管ODE在观察间隔之间产生平滑的隐藏状态，但当新观察到达时，RNN会触发隐藏的状态跳跃，从而导致插值不连续性问题。为了解决此问题，我们提出了立方样条平滑补偿，这是一个独立的模块，对ODE-RNN的输出或隐藏状态进行了训练，可以端到端训练。我们得出其分析解决方案，并提供其理论插值误差结合。广泛的实验表明其在ODE-RNN和立方样条插值上的优点。
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.
