Imitation Learning Of Neural Spatio-temporal Point Processes

Abstract

We present a novel Neural Embedding Spatio-Temporal (NEST) point process model for spatio-temporal discrete event data and develop an efficient imitation learning (a type of reinforcement learning) based approach for model fitting. Despite the rapid development of one-dimensional temporal point processes for discrete event data, the study of spatial-temporal aspects of such data is relatively scarce. Our model captures complex spatio-temporal dependence between discrete events by carefully design a mixture of heterogeneous Gaussian diffusion kernels, whose parameters are parameterized by neural networks. This new kernel is the key that our model can capture intricate spatial dependence patterns and yet still lead to interpretable results as we examine maps of Gaussian diffusion kernel parameters. The imitation learning model fitting for the NEST is more robust than the maximum likelihood estimate. It directly measures the divergence between the empirical distributions between the train

Stats

• citations16
• S2 citations—
• github stars0
• HF likes0
• heat score9.23
• arxiv keyzhu2019imitation

Related papers

• Learning Temporal Point Processes Via Reinforcement Learning (2018)0.00
• Reinforcement Learning With Policy Mixture Model For Temporal Point Processes Clustering (2019)0.00
• Deep Reinforcement Learning Of Marked Temporal Point Processes (2018)0.00
• Inexact Iterative Numerical Linear Algebra For Neural Network-based Spectral Estimation And Rare-event Prediction (2023)8.35
• Backpropagation Through Time And Space: Learning Numerical Methods With Multi-agent Reinforcement Learning (2022)0.00
• Prediction And Control With Temporal Segment Models (2017)0.00
• Learning Optimal Integration Of Spatial And Temporal Information In Noisy Chemotaxis (2023)6.77
• Robust And Adaptive Temporal-difference Learning Using An Ensemble Of Gaussian Processes (2021)0.00