Timezone: »

 
Poster
Wasserstein Learning of Deep Generative Point Process Models
Shuai Xiao · Mehrdad Farajtabar · Xiaojing Ye · Junchi Yan · Xiaokang Yang · Le Song · Hongyuan Zha

Mon Dec 04 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #106 #None
in Posters Mon »

Point processes are becoming very popular in modeling asynchronous sequential data due to their sound mathematical foundation and strength in modeling a variety of real-world phenomena. Currently, they are often characterized via intensity function which limits model's expressiveness due to unrealistic assumptions on its parametric form used in practice. Furthermore, they are learned via maximum likelihood approach which is prone to failure in multi-modal distributions of sequences. In this paper, we propose an intensity-free approach for point processes modeling that transforms nuisance processes to a target one. Furthermore, we train the model using a likelihood-free leveraging Wasserstein distance between point processes. Experiments on various synthetic and real-world data substantiate the superiority of the proposed point process model over conventional ones.

Keywords: Generative Models · Time Series Analysis · Adversarial Networks

Author Information

Benjamin Xiao (Ant Financial)
Mehrdad Farajtabar (Georgia Tech)
Xiaojing Ye (Georgia State University)
Junchi Yan (Shanghai Jiao Tong University)
Xiaokang Yang (Shanghai Jiao Tong University)
Le Song (Ant Financial & Georgia Institute of Technology)
Hongyuan Zha (Georgia Tech)

More from the Same Authors