selected publications

2023

1. Optimizing Hyperparameters with Conformal Quantile Regression

   Salinas, D., Golebiowsk, J., Klein, A., Seeger, M., and Archambeau, C.

   In to appear at the International Conference on Machine Learning (ICML’23) 2023

   Bib PDF Code

   @inproceedings{salinas-icml23,
     title = {Optimizing Hyperparameters with Conformal Quantile Regression},
     author = {Salinas, D. and Golebiowsk, J. and Klein, A. and Seeger, M. and Archambeau, C.},
     booktitle = {to appear at the International Conference on Machine Learning (ICML'23)},
     year = {2023},
     pdf = {conformal_hpo.pdf},
     bibtex_show = {true},
     code = {https://github.com/awslabs/syne-tune}
   }

2022

1. Syne Tune: A Library for Large Scale Hyperparameter Tuning and Reproducible Research

   Salinas, D., Seeger, M., Klein, A., Perrone, V., Wistuba, M., and Archambeau, C.

   In First Conference on Automated Machine Learning (Main Track) 2022

   Bib PDF Code

   @inproceedings{salinas-automl22,
     title = {Syne Tune: A Library for Large Scale Hyperparameter Tuning and Reproducible Research},
     author = {Salinas, D. and Seeger, M. and Klein, A. and Perrone, V. and Wistuba, M. and Archambeau, C.},
     booktitle = {First Conference on Automated Machine Learning (Main Track)},
     year = {2022},
     pdf = {syne_tune.pdf},
     bibtex_show = {true},
     code = {https://github.com/awslabs/syne-tune}
   }

2. Automatic Termination for Hyperparameter Optimization

   Makarova, A., Shen, H., Perrone, V., Klein, A., Faddoul, J. B., Krause, A., Seeger, M., and Archambeau, C.

   In First Conference on Automated Machine Learning (Main Track) 2022

   Bib PDF Code

   @inproceedings{makarova-automl22,
     title = {Automatic Termination for Hyperparameter Optimization},
     author = {Makarova, A. and Shen, H. and Perrone, V. and Klein, A. and Faddoul, J. B. and Krause, A. and Seeger, M. and Archambeau, C.},
     booktitle = {First Conference on Automated Machine Learning (Main Track)},
     year = {2022},
     pdf = {termination_criterion.pdf},
     bibtex_show = {true},
     code = {https://github.com/amazon-science/bo-early-stopping}
   }

2021

1. BORE: Bayesian Optimization by Density-Ratio Estimation

   Tiao, L., Klein, A., Seeger, M., Bonilla, E., Archambeau, C., and Ramos, F.

   In Proceedings of the 38th International Conference on Machine Learning (ICML’21) 2021

   Bib PDF Code

   @inproceedings{tiao-icml21,
     title = {BORE: Bayesian Optimization by Density-Ratio Estimation},
     author = {Tiao, L. and Klein, A. and Seeger, M. and Bonilla, E. and Archambeau, C. and Ramos, F.},
     booktitle = {Proceedings of the 38th International Conference on Machine Learning (ICML'21)},
     year = {2021},
     pdf = {bore.pdf},
     bibtex_show = {true},
     code = {https://github.com/awslabs/syne-tune}
   }

2. Hyperparameter Transfer Learning with Adaptive Complexity

   Horváth, S., Klein, A., Richtarik, P., and Archambeau, C.

   In Proceedings of The 24th International Conference on Artificial Intelligence and Statistics (AISTATS’21) 2021

   Bib PDF

   @inproceedings{horvath-aistats21,
     title = {Hyperparameter Transfer Learning with Adaptive Complexity },
     author = {Horv{\'a}th, S. and Klein, A. and Richtarik, P. and Archambeau, C.},
     booktitle = {Proceedings of The 24th International Conference on Artificial Intelligence and Statistics (AISTATS'21)},
     year = {2021},
     pdf = {abrac.pdf},
     bibtex_show = {true}
   }

2019

1. Meta-Surrogate Benchmarking for Hyperparameter Optimization

   Klein, A., Dai, Z., Hutter, F., Lawrence, N., and Gonzalez, J.

   In Proceedings of the 32th International Conference on Advances in Neural Information Processing Systems (NIPS’19) 2019

   Bib PDF Code

   @inproceedings{klein-nips19,
     title = {Meta-Surrogate Benchmarking for Hyperparameter Optimization},
     author = {Klein, A. and Dai, Z. and Hutter, F. and Lawrence, N. and Gonzalez, J.},
     booktitle = {Proceedings of the 32th International Conference on Advances in Neural Information Processing Systems (NIPS'19)},
     year = {2019},
     pdf = {profet.pdf},
     bibtex_show = {true},
     code = {https://github.com/EmuKit/emukit/tree/main/emukit/examples/profet}
   }

2. NAS-Bench-101: Towards Reproducible Neural Architecture Search

   Ying, C., Klein, A., Real, E., Christiansen, E., Murphy, K., and Hutter, F.

   In Proceedings of the 36th International Conference on Machine Learning (ICML’19) 2019

   Bib PDF Code

   @inproceedings{ying-icml19,
     author = {Ying, C. and Klein, A. and Real, E. and Christiansen, E. and Murphy, K. and Hutter, F.},
     title = {{NAS-Bench-101}: Towards Reproducible Neural Architecture Search},
     booktitle = {Proceedings of the 36th International Conference on Machine Learning (ICML'19)},
     year = {2019},
     pdf = {nasbench101.pdf},
     bibtex_show = {true},
     code = {https://github.com/google-research/nasbench}
   }

2018

1. BOHB: Robust and Efficient Hyperparameter Optimization at Scale

   Falkner, S., Klein, A., and Hutter, F.

   In Proceedings of the 35th International Conference on Machine Learning (ICML#18) 2018

   Bib PDF Code

   @inproceedings{falkner-icml18,
     title = {{BOHB}: Robust and Efficient Hyperparameter Optimization at Scale},
     author = {Falkner, S. and Klein, A. and Hutter, F.},
     booktitle = {Proceedings of the 35th International Conference on Machine Learning (ICML#18)},
     year = {2018},
     pdf = {bohb.pdf},
     bibtex_show = {true},
     code = {https://github.com/automl/HpBandSter}
   }

2017

1. Fast Bayesian Optimization of Machine Learning Hyperparameters on Large Datasets

   Klein, A., Falkner, S., Bartels, S., Hennig, P., and Hutter, F.

   In Proceedings of the 18th International Conference on Artificial Intelligence and Statistics (AISTATS’17) 2017

   Bib PDF Code

   @inproceedings{klein-aistats17,
     author = {Klein, A. and Falkner, S. and Bartels, S. and Hennig, P. and Hutter, F.},
     title = {Fast {Bayesian} Optimization of Machine Learning Hyperparameters on Large Datasets},
     booktitle = {Proceedings of the 18th International Conference on Artificial Intelligence and Statistics (AISTATS'17)},
     year = {2017},
     pdf = {fabolas.pdf},
     bibtex_show = {true},
     code = {https://github.com/EmuKit/emukit/tree/main/emukit/examples/fabolas}
   }

2016

1. Bayesian Optimization with Robust Bayesian Neural Networks

   Springenberg, J. T., Klein, A., Falkner, S., and Hutter, F.

   In Proceedings of the 29th International Conference on Advances in Neural Information Processing Systems (NIPS’16) 2016

   Bib PDF Code

   @inproceedings{springenberg-nips16,
     title = {Bayesian Optimization with Robust Bayesian Neural Networks},
     author = {Springenberg, J. T. and Klein, A. and Falkner, S. and Hutter, F.},
     booktitle = {Proceedings of the 29th International Conference on Advances in Neural Information Processing Systems (NIPS'16)},
     year = {2016},
     pdf = {bohamiann.pdf},
     bibtex_show = {true},
     code = {https://github.com/automl/pybnn}
   }

2015

1. Efficient and Robust Automated Machine Learning

   Feurer, M., Klein, A., Eggensperger, K., Springenberg, J., Blum, M., and Hutter, F.

   In Proceedings of the 28th International Conference on Advances in Neural Information Processing Systems (NIPS’15) 2015

   Bib PDF Code

   @inproceedings{feurer-nips2015,
     booktitle = {Proceedings of the 28th International Conference on Advances in Neural Information Processing Systems (NIPS'15)},
     title = {Efficient and Robust Automated Machine Learning},
     author = {Feurer, M. and Klein, A. and Eggensperger, K. and Springenberg, J. and Blum, M. and Hutter, F.},
     year = {2015},
     pdf = {autosklearn.pdf},
     bibtex_show = {true},
     code = {https://github.com/automl/auto-sklearn}
   }