Runtime Performance Anomaly Diagnosis in Production HPC Systems Using Active Learning

Burak Aksar, Efe Sencan, Benjamin Schwaller, Omar Aaziz, Vitus J. Leung, Jim M. Brandt, Brian Kulis, Manuel Egele, Ayse K. Coskun. Runtime Performance Anomaly Diagnosis in Production HPC Systems Using Active Learning. IEEE Trans. Parallel Distrib. Syst., 35(4):693-706, April 2024. [doi]

@article{AksarSSALBKEC24,
  title = {Runtime Performance Anomaly Diagnosis in Production HPC Systems Using Active Learning},
  author = {Burak Aksar and Efe Sencan and Benjamin Schwaller and Omar Aaziz and Vitus J. Leung and Jim M. Brandt and Brian Kulis and Manuel Egele and Ayse K. Coskun},
  year = {2024},
  month = {April},
  doi = {10.1109/TPDS.2024.3365462},
  url = {https://doi.org/10.1109/TPDS.2024.3365462},
  researchr = {https://researchr.org/publication/AksarSSALBKEC24},
  cites = {0},
  citedby = {0},
  journal = {IEEE Trans. Parallel Distrib. Syst.},
  volume = {35},
  number = {4},
  pages = {693-706},
}