ML Anthology

Efficiency Through Procrastination: Approximately Optimal Algorithm Configuration with Runtime Guarantees

Robert Kleinberg, Kevin Leyton-Brown, Brendan Lucier
IJCAI 2017 pp. 2023-2031
doi:10.24963/IJCAI.2017/281 /ijcai/2017/kleinberg2017ijcai-efficiency/

Abstract

Algorithm configuration methods have achieved much practical success, but to date have not been backed by meaningful performance guarantees. We address this gap with a new algorithm configuration framework, Structured Procrastination. With high probability and nearly as quickly as possible in the worst case, our framework finds an algorithm configuration that provably achieves near optimal performance. Moreover, its running time requirements asymptotically dominate those of existing methods.

PDF IJCAI Semantic Scholar

Cite

Text

Kleinberg et al. "Efficiency Through Procrastination: Approximately Optimal Algorithm Configuration with Runtime Guarantees." International Joint Conference on Artificial Intelligence, 2017. doi:10.24963/IJCAI.2017/281

Markdown

[Kleinberg et al. "Efficiency Through Procrastination: Approximately Optimal Algorithm Configuration with Runtime Guarantees." International Joint Conference on Artificial Intelligence, 2017.](https://mlanthology.org/ijcai/2017/kleinberg2017ijcai-efficiency/) doi:10.24963/IJCAI.2017/281

BibTeX

@inproceedings{kleinberg2017ijcai-efficiency,
  title     = {{Efficiency Through Procrastination: Approximately Optimal Algorithm Configuration with Runtime Guarantees}},
  author    = {Kleinberg, Robert and Leyton-Brown, Kevin and Lucier, Brendan},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2017},
  pages     = {2023-2031},
  doi       = {10.24963/IJCAI.2017/281},
  url       = {https://mlanthology.org/ijcai/2017/kleinberg2017ijcai-efficiency/}
}