We present a novel attention-based model for discrete event data to capture complex non-linear temporal dependence structures. We borrow the idea from the attention mechanism and incorporate it into the point processes' conditional intensity function. We further introduce a novel score function using Fourier kernel embedding, whose spectrum is represented using neural networks, which drastically differs from the traditional dot-product kernel and can capture a more complex similarity structure. We establish our approach's theoretical properties and demonstrate our approach's competitive performance compared to the state-of-the-art for synthetic and real data.
@article{arxiv.2002.07281,
title = {Deep Fourier Kernel for Self-Attentive Point Processes},
author = {Shixiang Zhu and Minghe Zhang and Ruyi Ding and Yao Xie},
journal= {arXiv preprint arXiv:2002.07281},
year = {2021}
}