ClusterLog: Clustering Logs for Effective Log-based Anomaly Detection

no code implementations • 19 Jan 2023 • Chris Egersdoerfer, Dong Dai, Di Zhang

With the increasing prevalence of scalable file systems in the context of High Performance Computing (HPC), the importance of accurate anomaly detection on runtime logs is increasing.

Anomaly Detection Clustering +2

RLScheduler: An Automated HPC Batch Job Scheduler Using Reinforcement Learning

1 code implementation • 20 Oct 2019 • Di Zhang, Dong Dai, Youbiao He, Forrest Sheng Bao, Bing Xie

Today high-performance computing (HPC) platforms are still dominated by batch jobs.

reinforcement-learning Reinforcement Learning (RL) +1

Rare Disease Physician Targeting: A Factor Graph Approach

no code implementations • 19 Jan 2017 • Yong Cai, Yunlong Wang, Dong Dai

For a specified rare disease, only a small number of patients are affected and a fractional of physicians are involved.

Aggregation of Affine Estimators

no code implementations • 12 Nov 2013 • Dong Dai, Philippe Rigollet, Lucy Xia, Tong Zhang

While results indicate that the same aggregation scheme may not satisfy sharp oracle inequalities with high probability, we prove that a weaker notion of oracle inequality for EW that holds with high probability.

Model Selection

Greedy Model Averaging

no code implementations • NeurIPS 2011 • Dong Dai, Tong Zhang

The purpose of this paper is to present a new greedy model averaging procedure that improves EWMA.

Model Selection