Automated Machine Learning with Monte-Carlo Tree Search

Created by W.Langdon from gp-bibliography.bib Revision:1.7615

@InProceedings{DBLP:conf/ijcai/RakotoarisonSS19,

• author = "Herilalaina Rakotoarison and Marc Schoenauer and Michele Sebag",
• title = "Automated Machine Learning with {Monte-Carlo Tree Search}",
• booktitle = "Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI 2019",
• year = "2019",
• editor = "Sarit Kraus",
• pages = "3296--3303",
• address = "Macao, China",
• month = aug # " 10-16",
• publisher = "ijcai.org",
• keywords = "genetic algorithms, genetic programming, TPOT, Machine Learning: Classification, Machine Learning: Ensemble Methods, Uncertainty in AI: Sequential Decision Making",
• timestamp = "Tue, 20 Aug 2019 16:18:18 +0200",
• biburl = "https://dblp.org/rec/conf/ijcai/RakotoarisonSS19.bib",
• bibsource = "dblp computer science bibliography, https://dblp.org",
• URL = "https://www.ijcai.org/proceedings/2019/0457.pdf",
• URL = "https://doi.org/10.24963/ijcai.2019/457",
• DOI = "doi:10.24963/ijcai.2019/457",
• size = "8 pages",
• abstract = "The AutoML task consists of selecting the proper algorithm in a machine learning portfolio, and its hyperparameter values, in order to deliver the best performance on the dataset at hand. MOSAIC, a Monte-Carlo tree search (MCTS) based approach,is presented to handle the AutoML hybrid structural and parametric expensive black-box optimisation problem. Extensive empirical studies are conducted to independently assess and compare: i-- the optimisation processes based on Bayesian optimisation or MCTS; ii-- its warm-start initialisation; iii-- the ensembling of the solutions gathered along the search. MOSAIC is assessed on the OpenML 100 benchmark and the Scikit-learn portfolio, with statistically significant gains over AUTO-SKLEARN, winner of former international AutoML challenges.",
• notes = "Comparison with TPOT",

}

Genetic Programming entries for Herilalaina Rakotoarison Marc Schoenauer Michele Sebag

Citations