| Automated Machine Learning with Monte-Carlo Tree Search H Rakotoarison, M Schoenauer, M Sebag International Joint Conference on Artificial Intelligence 2019, 2019 | 67 | 2019 |
| Black-box optimization revisited: Improving algorithm selection wizards through massive benchmarking L Meunier, H Rakotoarison, PK Wong, B Roziere, J Rapin, O Teytaud, ... IEEE Transactions on Evolutionary Computation 26 (3), 490-500, 2021 | 34 | 2021 |
| Learning meta-features for AutoML H Rakotoarison*, L Milijaona*, A Rasoanaivo, M Sebag, M Schoenauer International Conference on Learning Representations, 2022 | 20 | 2022 |
| AutoML with Monte Carlo Tree Search H Rakotoarison, M Sebag AutoML@ICML 2018, 2018 | 8 | 2018 |
| Efficient bayesian learning curve extrapolation using prior-data fitted networks S Adriaensen*, H Rakotoarison*, S Müller, F Hutter Neural Information Processing Systems, 2023 | 7 | 2023 |
| Distribution-based invariant deep networks for learning meta-features G De Bie, H Rakotoarison, G Peyré, M Sebag arXiv preprint arXiv:2006.13708, 2020 | 4 | 2020 |
| In-Context Freeze-Thaw Bayesian Optimization for Hyperparameter Optimization H Rakotoarison, S Adriaensen, N Mallik, S Garibov, E Bergman, F Hutter arXiv preprint arXiv:2404.16795, 2024 | | 2024 |
| Some contributions to AutoML: hyper-parameter optimization and meta-learning H Rakotoarison Université Paris-Saclay, 2022 | | 2022 |
| Results from the Joint Nevergrad and IOHprofiler Open Optimization Competition T Bäck, P Bennet, J de Nobel, C Doerr, J Dreo, H Rakotoarison, J Rapin, ... | | 2021 |
Michele SebagSenior ResearcherAdresse e-mail validée de lri.fr
