LGAIMLJan 21, 2018

Decoupled Learning for Factorial Marked Temporal Point Processes

arXiv:1801.06805v120 citationsHas Code
Originality Incremental advance
AI Analysis

This work addresses the computational challenge in modeling complex event data with multiple markers, offering an incremental improvement for applications in temporal point process analysis.

The paper tackles the problem of learning factorial marked temporal point processes, where events are factored into multiple markers, by proposing a decoupled learning method with efficient algorithms like ADMM and FISTA, and a reformulation into logistic regression, achieving demonstrated efficiency on real-world datasets.

This paper introduces the factorial marked temporal point process model and presents efficient learning methods. In conventional (multi-dimensional) marked temporal point process models, event is often encoded by a single discrete variable i.e. a marker. In this paper, we describe the factorial marked point processes whereby time-stamped event is factored into multiple markers. Accordingly the size of the infectivity matrix modeling the effect between pairwise markers is in power order w.r.t. the number of the discrete marker space. We propose a decoupled learning method with two learning procedures: i) directly solving the model based on two techniques: Alternating Direction Method of Multipliers and Fast Iterative Shrinkage-Thresholding Algorithm; ii) involving a reformulation that transforms the original problem into a Logistic Regression model for more efficient learning. Moreover, a sparse group regularizer is added to identify the key profile features and event labels. Empirical results on real world datasets demonstrate the efficiency of our decoupled and reformulated method. The source code is available online.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes