Timezone: »
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.
Author Information
Tsuyoshi Ide (IBM Research)
Georgios Kollias (International Business Machines)
Dzung Phan (IBM Research, T. J. Watson Research Center)
Naoki Abe (IBM Research AI)
More from the Same Authors
-
2021 Poster: FedDR – Randomized Douglas-Rachford Splitting Algorithms for Nonconvex Federated Composite Optimization »
Quoc Tran Dinh · Nhan H Pham · Dzung Phan · Lam Nguyen -
2021 Poster: Ensembling Graph Predictions for AMR Parsing »
Thanh Lam Hoang · Gabriele Picco · Yufang Hou · Young-Suk Lee · Lam Nguyen · Dzung Phan · Vanessa Lopez · Ramon Fernandez Astudillo -
2020 Poster: A Scalable MIP-based Method for Learning Optimal Multivariate Decision Trees »
Haoran Zhu · Pavankumar Murali · Dzung Phan · Lam Nguyen · Jayant Kalagnanam -
2013 Poster: Solving inverse problem of Markov chain with partial observations »
Tetsuro Morimura · Takayuki Osogami · Tsuyoshi Ide -
2009 Poster: Grouped Orthogonal Matching Pursuit for Variable Selection and Prediction »
Aurelie Lozano · Grzegorz M Swirszcz · Naoki Abe