Poster

Deep Fourier Kernel for Self-Attentive Point Processes

Shixiang Zhu · Minghe Zhang · Ruyi Ding · Yao Xie

Keywords: [ Models and Methods ] [ Time Series and Sequence Models ]

[ Abstract ]
Wed 14 Apr 6 a.m. PDT — 8 a.m. PDT
 
Oral presentation: Deep Learning / High-dimensionality
Thu 15 Apr 2:15 p.m. PDT — 3:15 p.m. PDT

Abstract:

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.

Chat is not available.