Deep Attention Point Processes with Neural Spectrum Fourier Kernel

We present a novel attention-based model for discrete event data to capture complex non-linear temporal dependence structure. We borrow the idea from the attention mechanism and incorporate it into the conditional intensity function of the point processes. We further introduce a novel score function using Fourier kernel embedding, whose spectrum is represented using neural networks, which drastically differ from the traditional dot-product kernel and can capture a more complex similarity structure. We establish the theoretical properties of our approach and demonstrate our approach's competitive performance compared to the state-of-the-art for synthetic and real data.