Saved in:
Bibliographic Details
Main Authors: Idé, Tsuyoshi, Kollias, Georgios, Phan, Dzung T., Abe, Naoki
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2208.10671
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913665460994048
author Idé, Tsuyoshi
Kollias, Georgios
Phan, Dzung T.
Abe, Naoki
author_facet Idé, Tsuyoshi
Kollias, Georgios
Phan, Dzung T.
Abe, Naoki
contents We propose a new sparse Granger-causal learning framework for temporal event data. We focus on a specific class of point processes called the Hawkes process. We begin by pointing out that most of the existing sparse causal learning algorithms for the Hawkes process suffer from a singularity in maximum likelihood estimation. As a result, their sparse solutions can appear only as numerical artifacts. In this paper, we propose a mathematically well-defined sparse causal learning framework based on a cardinality-regularized Hawkes process, which remedies the pathological issues of existing approaches. We leverage the proposed algorithm for the task of instance-wise causal event analysis, where sparsity plays a critical role. We validate the proposed framework with two real use-cases, one from the power grid and the other from the cloud data center management domain.
format Preprint
id arxiv_https___arxiv_org_abs_2208_10671
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Cardinality-Regularized Hawkes-Granger Model
Idé, Tsuyoshi
Kollias, Georgios
Phan, Dzung T.
Abe, Naoki
Machine Learning
Artificial Intelligence
Methodology
We propose a new sparse Granger-causal learning framework for temporal event data. We focus on a specific class of point processes called the Hawkes process. We begin by pointing out that most of the existing sparse causal learning algorithms for the Hawkes process suffer from a singularity in maximum likelihood estimation. As a result, their sparse solutions can appear only as numerical artifacts. In this paper, we propose a mathematically well-defined sparse causal learning framework based on a cardinality-regularized Hawkes process, which remedies the pathological issues of existing approaches. We leverage the proposed algorithm for the task of instance-wise causal event analysis, where sparsity plays a critical role. We validate the proposed framework with two real use-cases, one from the power grid and the other from the cloud data center management domain.
title Cardinality-Regularized Hawkes-Granger Model
topic Machine Learning
Artificial Intelligence
Methodology
url https://arxiv.org/abs/2208.10671