Uni-Logo
Also see my Google scholar profile.

2020

  • Liu, Zhengying and Pavao, Adrien and Xu, Zhen and Escalera, Sergio and Ferreira, Fabio and Guyon, Isabelle and Hong, Sirui and Hutter, Frank and Ji, Rongrong and Jacques Junior, Julio C S and Li, Ge and Lindauer, Marius and Luo, Zhipeng and Madadi, Meysam and Nierhoff, Thomas and Niu, Kangning and Pan, Chunguang and Stoll, Danny and Treguer, Sebastien and Wang, Jin and Wang, Peng and Wu, Chenglin and Xiong, Youcheng and Zela, Arber and Zhang, Yang (arXiv)(pdf)(bib)
    Winning solutions and post-challenge analyses of the ChaLearn AutoDL challenge 2019
    In: hal-02957135 (2020)
  • Lukasik, Jovita and Friede, David and Zela, Arber and Stuckenschmidt, Heiner and Hutter, Frank and Keuper, Margret (arXiv)(pdf)(bib)
    Smooth Variational Graph Embeddings for Efficient Neural Architecture Search
    In: arXiv:2010.04683 [cs.LG] (2020)
  • Rajan, Raghu and Diaz, Jessica Lizeth Borja and Guttikonda, Suresh and Ferreira, Fabio and Biedenkapp, André and Hutter, Frank (arXiv)(bib)
    MDP Playground: Controlling Dimensions of Hardness in Reinforcement Learning
    In: arXiv:1909.07750v3 [cs.LG] (2020)
  • Speck, David and Biedenkapp, André and Hutter, Frank and Mattmüller, Robert and Lindauer, Marius (arXiv)(bib)
    Learning Heuristic Selection with Dynamic Algorithm Configuration
    In: Workshop on Bridging the Gap Between AI Planning and Reinforcement Learning (PRL@ICAPS'20)
    (Video presentation)(Code)(Project Page)
  • Eggensperger, Katharina and Haase, Kai and Müller, Philipp and Lindauer, Marius and Hutter, Frank (arXiv)(bib)
    Neural Model-based Optimization with Right-Censored Observations
    In: arXiv:2009:13828 [cs.AI] (2020)
  • Franke, Jörg K. H. and Köhler, Gregor and Biedenkapp, André and Hutter, Frank (arXiv)(bib)
    Sample-Efficient Automated Deep Reinforcement Learning
    In: arXiv:2009.01555 [cs.LG] (2020)
  • Shala, Gresa and Biedenkapp, André and Awad, Noor and Adriaensen, Steven and Lindauer, Marius and Hutter, Frank (pdf)(poster)(bib)
    Learning Step-Size Adaptation in CMA-ES
    In: Proceedings of the Sixteenth International Conference on Parallel Problem Solving from Nature (PPSN'20)
    (Video presentation)(Code)(Project Page)
  • Siems, Julien and Zimmer, Lucas and Zela, Arber and Lukasik, Jovita and Keuper, Margret and Hutter, Frank (arXiv)(pdf)(bib)
    NAS-Bench-301 and the Case for Surrogate Benchmarks for Neural Architecture Search
    In: arXiv:2008.09777 [cs.LG] (2020)
  • Feurer, Matthias and Eggensperger, Katharina and Falkner, Stefan and Lindauer, Marius and Hutter, Frank (arXiv)(bib)
    Auto-sklearn 2.0: The Next Generation
    In: arXiv:2007:04074 [cs.LG] (2020)
  • Eimer, Theresa and Biedenkapp, André and Hutter, Frank and Lindauer, Marius (pdf)(bib)
    Towards Self-Paced Context Evaluations for Contextual Reinforcement Learning
    In: Workshop on Inductive Biases, Invariances and Generalization in RL (BIG@ICML'20)
    (Video presentation)(Code)
  • Biedenkapp, André and Rajan, Raghu and Hutter, Frank and Lindauer, Marius (pdf)(slides)(bib)
    Towards TempoRL: Learning When to Act
    In: Workshop on Inductive Biases, Invariances and Generalization in RL (BIG@ICML'20)
    (Video presentation)(Code)
  • Souza, Artur and Nardi, Luigi and Oliveira, Leonardo B. and Olukotun, Kunle and Lindauer, Marius and Hutter, Frank (arXiv)(bib)
    Prior-guided Bayesian Optimization
    In: arXiv:2006.14608 [cs.LG] (2020)
  • Zimmer, Lucas and Lindauer, Marius and Hutter, Frank (arXiv)(bib)
    Auto-PyTorch Tabular: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL
    In: arXiv:2006.13799 [cs.LG] (2020)
  • Gargiani, Matilde and Zanelli, Andrea and Diehl, Moritz and Hutter, Frank (arXiv)(bib)
    On the Promise of the Stochastic Generalized Gauss-Newton Method for Training DNNs
    In: arXiv:2006.02409 [cs.LG] (2020)
  • Zaidi, Sheheryar and Zela, Arber and Elsken, Thomas and Holmes, Chris and Hutter, Frank and Teh, Yee Whye (arXiv)(pdf)(slides)(bib)
    Neural Ensemble Search for Performant and Calibrated Predictions
    In: Workshop on Uncertainty and Robustness in Deep Learning (UDL@ICML`20) (2020)
    Oral Presentation (Video presentation)(Code)
  • Elsken, Thomas and Staffler, Benedikt and Metzen, Jan Hendrik and Hutter, Frank (arXiv)(published)(pdf)(bib)
    Meta-Learning of Neural Architectures for Few-Shot Learning
    In: The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
    Oral Presentation (Top 6%)
  • Biedenkapp, André and Bozkurt, H. Furkan and Eimer, Theresa and Hutter, Frank and Lindauer, Marius (published)(pdf)(bib)
    Dynamic Algorithm Configuration: Foundation of a New Meta-Algorithmic Framework
    In: Proceedings of the Twenty-fourth European Conference on Artificial Intelligence (ECAI'20)
    (Video presentation)(Code)(Project Page)
  • Awad, N. and Mallik, N. and Hutter, F. (pdf)(poster)(bib)
    Differential Evolution for Neural Architecture Search
    In: Proceedings of the 1st workshop on neural architecture search(@ICLR'20)
    (Video presentation)(Code)
  • Volpp, Michael and Fröhlich, Lukas P. and Fischer, Kirsten and Doerr, Andreas and Falkner, Stefan and Hutter, Frank and Daniel, Christian (arXiv)(bib)
    Meta-Learning Acquisition Functions for Transfer Learning in Bayesian Optimization
    In: International Conference on Learning Representations
  • Gargiani, Matilde and Zanelli, Andrea and Tran-Dinh, Quoc and Diehl, Moritz and Hutter, Frank (arXiv)(bib)
    Transferring Optimally Across Data Distrutions via Homotopy Methods
    In: International Conference on Learning Representations
  • Tomašev, Nenad and Cornebise, Julien and Hutter, Frank and Mohamed, Shakir and Khan, Mohammad Emtiyaz and De Winne, Ruben and Schaul, Tom and Clopath, Claudia (arXiv)(bib)
    AI for social good: unlocking the opportunity for positive impact
    In: Nature Communications 11.1 (2020)
  • Zela, Arber and Elsken, Thomas and Saikia, Tonmoy and Marrakchi, Yassine and Brox, Thomas and Hutter, Frank (arXiv)(published)(pdf)(slides)(bib)
    Understanding and Robustifying Differentiable Architecture Search
    In: International Conference on Learning Representations
    Oral Presentation (Top 7%)
  • Zela, Arber and Siems, Julien and Hutter, Frank (arXiv)(published)(pdf)(slides)(bib)
    NAS-Bench-1Shot1: Benchmarking and Dissecting One-shot Neural Architecture Search
    In: International Conference on Learning Representations

2019

  • Rajan, Raghu and Hutter, Frank (arXiv)(pdf)(bib)
    MDP Playground: Meta-Features in Reinforcement Learning
    In: NeurIPS 2019 Deep RL Workshop
  • Feurer, Matthias and van Rijn, Jan N. and Kadra, Arlind and Gijsbers, Pieter and Mallik, Neeratyoy and Ravi, Sahithya and Müller, Andreas and Vanschoren, Joaquin and Hutter, Frank (arXiv)(bib)
    OpenML-Python: an extensible Python API for OpenML
    In: arXiv 1911.02490 (2019): 1-5
  • Lindauer, Marius and Hutter, Frank (arXiv)(bib)
    Best Practices for Scientific Research on Neural Architecture Search
    In: arXiv:1909.02453 [cs.LG] (2019)
  • Bischl, Bernd and Casalicchio, Giuseppe and Feurer, Matthias and Hutter, Frank and Lang, Michel and Mantovani, Rafael G. and van Rijn, Jan N. and Vanschoren, Joaquin (arXiv)(bib)
    OpenML Benchmarking Suites
    In: arXiv 1708.0373v2 (2019): 1-6
  • Lindauer, Marius and Feurer, Matthias and Eggensperger, Katharina and Biedenkapp, André and Hutter, Frank (arXiv)(slides)(bib)
    Towards Assessing the Impact of Bayesian Optimization's Own Hyperparameters
    In: IJCAI 2019 DSO Workshop
  • Biedenkapp, André and Bozkurt, H. Furkan and Hutter, Frank and Lindauer, Marius (arXiv)(pdf)(bib)
    Towards White-box Benchmarks for Algorithm Control
    In: IJCAI 2019 DSO Workshop
    (Project Page)
  • Lindauer, Marius and Eggensperger, Katharina and Feurer, Matthias and Biedenkapp, André and Marben, Joshua and Müller, Philipp and Hutter, Frank (arXiv)(bib)
    BOAH: A Tool Suite for Multi-Fidelity Bayesian Optimization & Analysis of Hyperparameters
    In: arXiv:1908.06756 [cs.LG] (2019)
    (Code)(Project Page)
  • Fuks, L. and Awad, N. and Hutter, F. and Lindauer, M. (pdf)(bib)
    An Evolution Strategy with Progressive Episode Lengths for Playing Games
    In: Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI’19)
  • Gargiani, M. and Klein, A. and Falkner, S. and Hutter, F. (published)(bib)
    Probabilistic Rollouts for Learning Curve Extrapolation Across Hyperparameter Settings
    In: 6th ICML Workshop on Automated Machine Learning
  • Feurer, Matthias and Hutter, Frank (arXiv)(published)(bib)
    Hyperparameter Optimization
    In: AutoML: Methods, Sytems, Challenges
  • Mendoza, Hector and Klein, Aaron and Feurer, Matthias and Springenberg, Jost Tobias and Urban, Matthias and Burkart, Michael and Dippel, Max and Lindauer, Marius and Hutter, Frank (arXiv)(published)(bib)
    Towards Automatically-Tuned Deep Neural Networks
    In: AutoML: Methods, Sytems, Challenges
  • Feurer, Matthias and Klein, Aaron and Eggensperger, Katharina and Springenberg, Jost and Blum, Manuel and Hutter, Frank (arXiv)(published)(bib)
    Auto-sklearn: Efficient and Robust Automated Machine Learning
    In: AutoML: Methods, Systems, Challenges
  • Elsken, Thomas and Metzen, Jan Hendrik and Hutter, Frank (arXiv)(pdf)(bib)
    Neural Architecture Search: A Survey
    In: Journal of Machine Learning Research 20.55 (2019): 1-21
  • Hutter, Frank and Kotthoff, Lars and Vanschoren, Joaquin (published)(bib)
    Automated Machine Learning - Methods, Systems, Challenges
    Springer
  • Elsken, Thomas and Metzen, Jan Hendrik and Hutter, Frank (arXiv)(published)(bib)
    Efficient Multi-Objective Neural Architecture Search via Lamarckian Evolution
    In: International Conference on Learning Representations
  • Eggensperger, Katharina and Lindauer, Marius and Hutter, Frank (arXiv)(published)(bib)
    Pitfalls and Best Practices in Algorithm Configuration
    In: Journal of Artificial Intelligence Research (JAIR) 64 (2019): 861--893
  • Klein, Aaron and Dai, Zhenwen and Hutter, Frank and Lawrence, Neil and Gonzalez, Javier (published)(bib)
    Meta-Surrogate Benchmarking for Hyperparameter Optimization
    In: Advances in Neural Information Processing Systems 32
  • Saikia, T. and Marrakchi, Y. and Zela, A. and Hutter, F. and Brox, T. (arXiv)(published)(pdf)(bib)
    AutoDispNet: Improving Disparity Estimation With AutoML
    In: IEEE International Conference on Computer Vision (ICCV)
  • Runge, Frederic and Stoll, Danny and Falkner, Stefan and Hutter, Frank (arXiv)(pdf)(bib)
    Learning to Design RNA
    In: International Conference on Learning Representations
  • Loshchilov, Ilya and Hutter, Frank (arXiv)(published)(bib)
    Decoupled Weight Decay Regularization
    In: International Conference on Learning Representations
  • Franke, Jörg KH and Köhler, Gregor and Awad, Noor and Hutter, Frank (arXiv)(pdf)(bib)
    Neural Architecture Evolution in Deep Reinforcement Learning for Continuous Control
    In: NeurIPS 2019 Workshop on Meta-Learning (2019)
  • Ying, Chris and Klein, Aaron and Real, Esteban and Christiansen, Eric and Murphy, Kevin and Hutter, Frank (arXiv)(pdf)(bib)
    Nas-bench-101: Towards reproducible neural architecture search
    In: Thirty-sixth International Conference on Machine Learning

2018

  • Schirrmeister, R. and Chrabąszcz, P. and Hutter, F. and Ball, T. (arXiv)(poster)(bib)
    Training Generative Reversible Networks
    In: ICML 2018 workshop on Theoretical Foundations and Applications of Deep Generative Models
  • Chrabąszcz, Patryk and Loshchilov, Ilya and Hutter, Frank (arXiv)(published)(pdf)(bib)
    Back to Basics: Benchmarking Canonical Evolution Strategies for Playing Atari
    In: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI-18
  • Eggensperger, Katharina and Lindauer, Marius and Hutter, Frank (arXiv)(published)(poster)(slides)(bib)
    Neural Networks for Predicting Algorithm Runtime Distributions
    In: Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI’18)
  • Falkner, Stefan and Klein, Aaron and Hutter, Frank (published)(pdf)(supplementary)(poster)(bib)
    BOHB: Robust and Efficient Hyperparameter Optimization at Scale
    In: Proceedings of the 35th International Conference on Machine Learning (ICML 2018)
  • Feurer, Matthias and Eggensperger, Katharina and Falkner, Stefan and Lindauer, Marius and Hutter, Frank (pdf)(bib)
    Practical Automated Machine Learning for the AutoML Challenge 2018
    In: ICML 2018 AutoML Workshop
  • Feurer, M. and Hutter, F. (pdf)(bib)
    Towards Further Automation in AutoML
    In: ICML 2018 AutoML Workshop
  • Zela, Arber and Klein, Aaron and Falkner, Stefan and Hutter, Frank (pdf)(poster)(bib)
    Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search
    In: ICML 2018 AutoML Workshop
  • Biedenkapp, André and Marben, Joshua and Lindauer, Marius and Hutter, Frank (pdf)(slides)(bib)
    CAVE: Configuration Assessment, Visualization and Evaluation
    In: Proceedings of the International Conference on Learning and Intelligent Optimization (LION'18)
    (Video presentation)(Code)(Project Page)
  • Elsken, Thomas and Metzen, Jan Hendrik and Hutter, Frank (arXiv)(bib)
    Efficient Multi-objective Neural Architecture Search via Lamarckian Evolution
    In: ArXiv e-prints 1804.09081 (2018)
  • Lindauer, M. and Hutter, F. (arXiv)(published)(bib)
    Warmstarting of Model-based Algorithm Configuration
    In: Proceedings of the AAAI conference
  • Ilg, Eddy and Cicek, Oezguen and Galesso, Silvio and Klein, Aaron and Makansi, Osama and Hutter, Frank and Brox, Thomas (arXiv)(pdf)(bib)
    Uncertainty Estimates for Optical Flow with Multi-Hypotheses Networks
    In: Proceedings of ECCV 2018
  • van Rijn, J.N. and Hutter, F. (arXiv)(published)(bib)
    Hyperparameter Importance Across Datasets
    In: SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2018)
  • Eggensperger, Katharina and Lindauer, Marius and Hoos, Holger H. and Hutter, Frank and Leyton-Brown, Kevin (arXiv)(published)(bib)
    Efficient Benchmarking of Algorithm Configurators via Model-Based Surrogates
    In: Machine Learning 107 (2018): 15-41
  • Wilson, James and Hutter, Frank and Deisenroth, Marc (published)(bib)
    Maximizing acquisition functions for Bayesian optimization
    In: Advances in Neural Information Processing Systems 31
  • Lehman, J. and Clune, J. and Misevic, D. and Adami, C. and Beaulieu, J. and Bentley, P. J. and Bernard, S. and Beslon, G. and Bryson, D. M. and Chrabaszcz, P. and Cheney, N. and Cully, A. and Doncieux, S. and Dyer, F. C. and Ellefsen, K. O. and Feldt, R. and Fischer, S. and Forrest, S. and Fr{\'{e}}noy, A. and Gagn{\'{e}}, C. and Goff, L. K. Le and Grabowski, L. M. and Hodjat, B. and Hutter, F. and Keller, L. and Knibbe, C. and Krcah, P. and Lenski, R. E. and Lipson, H. and MacCurdy, R. and Maestre, C. and Miikkulainen, R. and Mitri, S. and Moriarty, D. E. and Mouret, J.{-}B. and Nguyen, A. and Ofria, C. and Parizeau, M. and Parsons, D. P. and Pennock, R. T. and Punch, W. F. and Ray, T. S. and Schoenauer, M. and Shulte, E. and Sims, K. and Stanley, K. O. and Taddei, F. and Tarapore, D. and Thibault, S. and Weimer, W. and Watson, R. and Yosinksi, J. (arXiv)(bib)
    The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities
    In: CoRR abs/1803.03453 (2018)
  • Wilson, Dennis and Rodrigues, Silvio and Segura, Carlos and Loshchilov, Ilya and Hutter, Frank and Buenfil, Guillermo López and Kheiri, Ahmed and Keedwell, Ed and Ocampo-Pineda, Mario and Özcan, Ender and Peña, Sergio Ivvan Valdez and Goldman, Brian and Rionda, Salvador Botello and Hernández-Aguirre, Arturo and Veeramachaneni, Kalyan and Cussat-Blanc, Sylvain (published)(bib)
    Evolutionary computation for wind farm layout optimization
    In: Renewable Energy 126 (2018): 681 - 691
    (summary)(summary bibtex)

2017

  • Falkner, S. and Klein, A. and Hutter, F. (pdf)(bib)
    Combining Hyperband and Bayesian Optimization
    In: NIPS 2017 Bayesian Optimization Workshop
  • Klein, A. and Falkner, S. and Mansur, N. and Hutter, F. (pdf)(bib)
    RoBO: A Flexible and Robust Bayesian Optimization Framework in Python
    In: NIPS 2017 Bayesian Optimization Workshop
  • Elsken, Thomas and Metzen, Jan Hendrik and Hutter, Frank (arXiv)(pdf)(bib)
    Simple And Efficient Architecture Search for Convolutional Neural Networks
    In: NIPS Workshop on Meta-Learning
  • Bischl, Bernd and Casalicchio, Giuseppe and Feurer, Matthias and Hutter, Frank and Lang, Michel and Mantovani, Rafael G. and van Rijn, Jan N. and Vanschoren, Joaquin (arXiv)(bib)
    OpenML Benchmarking Suites and the OpenML100
    In: arXiv 1708.0373v1 (2017): 1-6
  • Greff, K. and Klein, A. and Chovanec, M. and Hutter, F. and Schmidhuber, J. (pdf)(bib)
    The Sacred Infrastructure for Computational Research
    In: Proceedings of the 15th Python in Science Conference (SciPy 2017)
  • Lindauer, M. and Hoos, H. and Hutter, F. and Schaub, T. (pdf)(bib)
    AutoFolio: An Automatically Configured Algorithm Selector (Extended Abstract)
    In: Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI'17)
  • Klein, A. and Falkner, S. and Springenberg, J. T. and Hutter, F. (pdf)(bib)
    Learning Curve Prediction with Bayesian Neural Networks
    In: International Conference on Learning Representations (ICLR) 2017 Conference Track
  • Loshchilov, I. and Hutter, F. (pdf)(bib)
    SGDR: Stochastic Gradient Descent with Warm Restarts
    In: International Conference on Learning Representations (ICLR) 2017 Conference Track
  • Wagner, M. and Lindauer, M. and Misir, M. and Nallaperuma, S. and Hutter, F. (published)(pdf)(bib)
    A case study of algorithm selection for the traveling thief problem
    In: Journal of Heuristics (2017): 1-26
  • Biedenkapp, André and Lindauer, Marius and Eggensperger, Katharina and Fawcett, Chris and Hoos, Holger H. and Hutter, Frank (pdf)(poster)(bib)
    Efficient Parameter Importance Analysis via Ablation with Surrogates
    In: Proceedings of the Thirty-First Conference on Artificial Intelligence (AAAI'17)
    (Code)(Project Page)
  • Lindauer, M. and Hutter, F. (published)(bib)
    Pitfalls and Best Practices for Algorithm Configuration (Breakout Session Report)
    In: Dagstuhl Reports 6 (2017): 70-72
  • Hutter, F. and Lindauer, M. and Balint, A. and Bayless, S. and Hoos, H. and Leyton-Brown, K. (arXiv)(published)(bib)
    The Configurable SAT Solver Challenge (CSSC)
    In: Artificial Intelligence Journal (AIJ) 243 (2017): 1-25
  • van Rijn, J. N. and Hutter, F. (pdf)(bib)
    An Empirical Study of Hyperparameter Importance Across Datasets
    In: Proceedings of the International Workshop on Automatic Selection, Configuration and Composition of Machine Learning Algorithms (AutoML 2017)
  • Klein, A. and Falkner, S. and Bartels, S. and Hennig, P. and Hutter, F. (pdf)(bib)
    Fast Bayesian Optimization of Machine Learning Hyperparameters on Large Datasets
    In: Proceedings of the AISTATS conference
  • Klein, A. and Falkner, S. and Bartels, S. and Hennig, P. and Hutter, F. (pdf)(bib)
    Fast Bayesian hyperparameter optimization on large datasets
    In: Electronic Journal of Statistics
  • Schirrmeister, Robin and Springenberg, Jost Tobias and Fiederer, Lukas and Glasstetter, Martin and Eggensperger, Katharina and Tangermann, Michael and Hutter, Frank and Burgard, Wolfram and Ball, Tonio (arXiv)(published)(bib)
    Deep learning with convolutional neural networks for EEG decoding and visualization
    In: Human Brain Mapping 38 (2017): 5391--5420
  • Lindauer, M. and Hoos, H. and Hutter, F. and Leyton-Brown, K. (bib)
    Selection and Configuration of Parallel Portfolios
    In: Handbook of Parallel Constraint Reasoning
    To appear
  • Wilson, James and Moriconi, Riccardo and Hutter, Frank and Deisenroth, Marc Peter (published)(bib)
    The reparameterization trick for acquisition functions
    In: Proceedings of BayesOpt 2017

2016

  • Springenberg, J. T. and Klein, A. and Falkner, S. and Hutter, F. (pdf)(supplementary)(bib)
    Bayesian optimization with robust Bayesian neural networks
    In: Advances in Neural Information Processing Systems 29
  • Bischl, B. and Kerschke, P. and Kotthoff, L. and Lindauer, M. and Malitsky, Y. and Frechétte, A. and Hoos, H. and Hutter, F. and Leyton-Brown, K. and Tierney, K. and Vanschoren, J. (arXiv)(published)(bib)
    ASlib: A Benchmark Library for Algorithm Selection
    In: Artificial Intelligence Journal (AIJ) 237 (2016): 41-58
  • Mendoza, H. and Klein, A. and Feurer, M. and Springenberg, J. and Hutter, F. (pdf)(poster)(bib)
    Towards Automatically-Tuned Neural Networks
    In: ICML 2016 AutoML Workshop
  • Loshchilov, I. and Hutter, F. (pdf)(bib)
    Online Batch Selection for Faster Training of Neural Networks
    In: International Conference on Learning Representations (ICLR) 2016 Workshop Track
  • Loshchilov, I. and Hutter, F.
    CMA-ES for Hyperparameter Optimization of Deep Neural Networks
    In: International Conference on Learning Representations (ICLR) 2016 Workshop Track
  • Wang, Ziyu and Hutter, Frank and Zoghi, Masrour and Matheson, David and de Freitas, Nando (pdf)(bib)
    Bayesian Optimization in a Billion Dimensions via Random Embeddings
    In: Journal of Artificial Intelligence Research (JAIR) 55 (2016): 361-387
  • Meinel, Andreas and Eggensperger, Katharina and Tangermann, Michael and Hutter, Frank (pdf)(bib)
    Hyperparameter Optimization for Machine Learning Problems in BCI (Abstract)
    In: Proceedings of the International Brain Computer Interface Meeting 2016
  • Schubert, Tobias and Eggensperger, Katharina and Gkogkidis, Alexis and Hutter, Frank and Ball, Tonio and Burgard, Wolfram (pdf)(bib)
    Automatic Bone Parameter Estimation for Skeleton Tracking in Optical Motion Capture
    In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA'16)
    Video showing the results of the optimization procedure
  • Marius Lindauer, Rolf-David Bergdoll and Hutter, Frank (pdf)(bib)
    An Empirical Study of Per-Instance Algorithm Scheduling
    In: Proceedings of the International Conference on Learning and Intelligent Optimization (LION'16)

2015

  • Klein, A. and Bartels, S. and Falkner, S. and Hennig, P. and Hutter, F. (pdf)(bib)
    Towards efficient Bayesian Optimization for Big Data
    In: NIPS 2015 Bayesian Optimization Workshop
  • Feurer, Matthias and Klein, Aaron and Eggensperger, Katharina and Springenberg, Jost Tobias and Blum, Manuel and Hutter, Frank (preprint)(published)(supplementary)(poster)(bib)
    Efficient and Robust Automated Machine Learning
    In: Advances in Neural Information Processing Systems 28 (NeurIPS'15)
  • Falkner, S. and Lindauer, M. and Hutter, F. (pdf)(bib)
    SpySMAC: Automated Configuration and Performance Analysis of SAT Solvers
    In: Proceedings of the International Conference on Satisfiability Solving (SAT'15)
  • Lindauer, M. and Hoos, H. and Hutter, F. and Schaub, T. (pdf)(bib)
    AutoFolio: An automatically configured Algorithm Selector
    In: Journal of Artificial Intelligence 53 (2015): 745-778
  • Vallati, Mauro and Hutter, Frank and Chrpa, Lukáš and McCluskey, T.L. (pdf)(bib)
    On the Effective Configuration of Planning Domain Models
    In: Proceedings of the 24th International Joint Conference on Artificial Intelligence (IJCAI)
  • Frank Hutter and Lin Xu and Holger H. Hoos and Kevin Leyton-Brown (pdf)(bib)
    Algorithm runtime prediction: Methods & evaluation (extended abstract)
    In: Proceedings of the Journal Track of the 24th International Joint Conference on Artificial Intelligence (IJCAI)
  • Tobias Domhan and Jost Tobias Springenberg and Frank Hutter (pdf)(bib)
    Speeding up Automatic Hyperparameter Optimization of Deep Neural Networks by Extrapolation of Learning Curves
    In: Proceedings of the 24th International Joint Conference on Artificial Intelligence (IJCAI)
  • Hutter, F. and Lücke, J. and Schmidt-Thieme, L. (published)(bib)
    Beyond Manual Tuning of Hyperparameters
    In: Künstliche Intelligenz 0. (2015): 1-9
  • Feurer, Matthias and Klein, Aaron and Eggensperger, Katharina and Springenberg, Jost Tobias and Blum, Manuel and Hutter, Frank (pdf)(poster)(slides)(bib)
    Methods for Improving Bayesian Optimization for AutoML
    In: ICML 2015 AutoML Workshop
  • Marius Lindauer and Holger H. Hoos and Frank Hutter and Torsten Schaub (pdf)(bib)
    AutoFolio: Algorithm Configuration for Algorithm Selection
    In: Proceedings of the Twenty-Ninth AAAI Workshops on Artificial Intelligence
  • Jendrik Seipp, Silvan Sievers, Malte Helmert and Frank Hutter. (pdf)(bib)
    Automatic Configuration of Sequential Planning Portfolios
    In: Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence
  • Katharina Eggensperger and Frank Hutter and Holger H. Hoos and Kevin Leyton-Brown (pdf)(poster)(bib)
    Efficient Benchmarking of Hyperparameter Optimizers via Surrogates
    In: Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence
  • Matthias Feurer and Tobias Springenberg and Frank Hutter (pdf)(supplementary)(poster)(bib)
    Initializing Bayesian Hyperparameter Optimization via Meta-Learning
    In: Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence
  • Marius Lindauer and Holger H. Hoos and and Frank Hutter (pdf)(bib)
    From Sequential Algorithm Selection to Parallel Portfolio Selection
    In: Proceedings of the International Conference on Learning and Intelligent Optimization (LION'15)
  • Vanschoren, J. and Bischl, B. and Hutter, F. and Sebag, M. and Kegl, B. and Schmid, M. and Napolitano, G. and Wolstencroft, K. and Williams, A.R and Lawrence, N (pdf)(bib)
    Towards a Data Science Collaboratory
    In: Advances in Intelligent Data Analysis XIV (IDA 2015)

2014

  • Seipp, Jendrick and Sievers, Silvan and Hutter, Frank (pdf)(bib)
    Fast Downward SMAC
    Planner abstract, IPC 2014 Planning and Learning Track.
    Best basic solver award, and third place in the categories overall best quality and best learner.
  • Seipp, Jendrick and Sievers, Silvan and Hutter, Frank (pdf)(bib)
    Fast Downward Cedalion
    Planner abstract, IPC 2014 Planning and Learning Track.
    Best learner award, and second place in the category overall best quality at the IPC 2014 Planning and Learning Track. Also achieved the highest coverage in the IPC 2014 sequential agile planning track.
  • Eggensperger, Katharina and Hutter, Frank and Hoos, Holger H. and Leyton-Brown, Kevin (pdf)(slides)(bib)
    Surrogate Benchmarks for Hyperparameter Optimization
    In: ECAI workshop on Metalearning and Algorithm Selection (MetaSel)
    Superseeded by the AAAI15 paper Efficient Benchmarking of Hyperparameter Optimizers via Surrogates
  • Matthias Feurer and Tobias Springenberg and Frank Hutter (pdf)(slides)(bib)
    Using Meta-Learning to Initialize Bayesian Optimization of Hyperparameters
    In: ECAI workshop on Metalearning and Algorithm Selection (MetaSel)
    Superseeded by the AAAI15 paper Initializing Bayesian Hyperparameter Optimization via Meta-Learning
  • Chris Fawcett, Mauro Vallati, Frank Hutter, Jörg Hoffmann, Holger Hoos and Kevin Leyton-Brown (pdf)(bib)
    Improved Features for Runtime Prediction of Domain-Independent Planners
    In: Proceedings of the International Conference on Automated Planning and Scheduling (ICAPS 2014)
  • Frank Hutter and Holger Hoos and Kevin Leyton-Brown (pdf)(longversion)(bib)
    An Efficient Approach for Assessing Hyperparameter Importance
    In: Proceedings of International Conference on Machine Learning 2014 (ICML 2014)
  • Domhan, Tobias and Springenberg, Tobias and Hutter, Frank (pdf)(poster)(bib)
    Extrapolating Learning Curves of Deep Neural Networks
    In: ICML 2014 AutoML Workshop
  • Leyton-Brown, Kevin and Hoos, Holger and Hutter, Frank and Xu, Lin (preprint)(published)(bib)
    Understanding the Empirical Hardness of NP-complete Problems
    In: Communications of the Association for Computing Machinery (CACM) 57.5 (2014): 98--107
  • Daniel Geschwender, Frank Hutter, Lars Kotthoff, Yuri Malitsky, Holger Hoos and Kevin Leyton-Brown (pdf)(slides)(bib)
    Algorithm Configuration in the Cloud: A Feasibility Study
    In: Proceedings of the Learning and Intelligent OptimizatioN Conference (LION 8)
  • Frank Hutter, Manuel López-Ibáñez, Chris Fawcett, Marius Lindauer, Holger Hoos, Kevin Leyton-Brown and Thomas Stützle (pdf)(slides)(bib)
    AClib: a Benchmark Library for Algorithm Configuration
    In: Proceedings of the Learning and Intelligent OptimizatioN Conference (LION 8)
  • Frank Hutter and Lin Xu and Holger H. Hoos and Kevin Leyton-Brown (arXiv)(published)(bib)
    Algorithm runtime prediction: Methods & evaluation
    In: Artificial Intelligence 206.0 (2014): 79--111
    The data and source code for this paper are available from our Empirical Performance Models project page.

2013

  • Eggensperger, Katharina and Feurer, Matthias and Hutter, Frank and Bergstra, James and Snoek, Jasper and Hoos, Holger H. and Leyton-Brown, Kevin (pdf)(poster)(bib)
    Towards an Empirical Foundation for Assessing Bayesian Optimization of Hyperparameters
    In: NeurIPS workshop on Bayesian Optimization in Theory and Practice
    Software and benchmarks are available from our HPOlib website.
  • Swersky, Kevin and Duvenaud, David and Snoek, Jasper and Hutter, Frank and Osborne, Michael (pdf)(bib)
    Raiders of the Lost Architecture: Kernels for Bayesian Optimization in Conditional Parameter Spaces
    In: NIPS workshop on Bayesian Optimization in Theory and Practice
  • Hutter, Frank and Hoos, Holger H. and Leyton-Brown, Kevin (pdf)(poster)(bib)
    An Efficient Approach for Assessing Parameter Importance in Bayesian Optimization
    In: NIPS workshop on Bayesian Optimization in Theory and Practice
  • Ziyu Wang and Masrour Zoghi and Frank Hutter and David Matheson and Nando de Freitas (arXiv)(pdf)(bib)
    Bayesian Optimization in High Dimensions via Random Embeddings
    In: Proceedings of the 23rd international joint conference on Artificial Intelligence (IJCAI)
    Distinguished paper award.
  • Chris Thornton and Frank Hutter and Holger H. Hoos and Kevin Leyton-Brown (pdf)(bib)
    Auto-WEKA: Combined Selection and Hyperparameter Optimization of Classification Algorithms
    In: Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'13)
    The software is available from our Auto-WEKA page.
  • Hutter, F. and Hoos, H. H. and Leyton-Brown, K. (pdf)(bib)
    An Evaluation of Sequential Model-Based Optimization for Expensive Blackbox Functions
    In: Proceedings of GECCO-13 Workshop on Blackbox Optimization Benchmarking (BBOB'13)
    Software and data are available from the SMAC page.
  • Hutter, F. and Hoos, H. H. and Leyton-Brown, K. (pdf)(bib)
    Identifying Key Algorithm Parameters and Instance Features using Forward Selection
    In: Proceedings of the 7th International Conference on Learning and Optimization (LION-7)
    The data and source code for this paper are available from our Empirical Performance Models project page.

2012

  • Lin Xu and Frank Hutter and Jonatahn Shen and Holger Hoos and Kevin Leyton-Brown (pdf)(bib)
    SATzilla2012: Improved Algorithm Selection Based on Cost-sensitive Classification Models
    In: Proceedings of SAT Challenge 2012: Solver and Benchmark Descriptions
    Solver description for the 2012 SAT challenge. SATzilla2012 won 3 out of the 4 categories for which it was eligible, and placed 2nd in the remaining one. Details: it won the sequential portfolio track, was the best solver for 2 of the 3 main sequential categories (Application and Hard Combinatorial), and 2nd in the sequential Random Category (beaten only by a new non-portfolio solver, CCASAT). See the SATzilla project page for details on SATzilla and source code.
  • Xu, Lin and Hutter, Frank and Hoos, Holger H. and Leyton-Brown, Kevin (pdf)(bib)
    Evaluating Component Solver Contributions to Portfolio-Based Algorithm Selectors
    In: International Conference on Theory and Applications of Satisfiability Testing (SAT'12)
  • Hutter, F. and Hoos, H. H. and Leyton-Brown, K. (pdf)(pptx)(bib)
    Parallel Algorithm Configuration
    In: Proceedings of the Learning and Intelligent OptimizatioN Conference LION 6

2011

  • Hutter, Frank and Hoos, Holger H. and Leyton-Brown, Kevin (pdf)(poster)(bib)
    Bayesian Optimization With Censored Response Data
    In: NIPS workshop on Bayesian Optimization, Sequential Experimental Design, and Bandits
    Published online. There is also a new, extended arXiv version.
  • Xu, Lin and Hutter, Frank and Hoos, Holger H. and Leyton-Brown, Kevin (pdf)(bib)
    Hydra-MIP: Automated Algorithm Configuration and Selection for Mixed Integer Programming
    In: RCRA workshop on Experimental Evaluation of Algorithms for Solving Problems with Combinatorial Explosion at the International Joint Conference on Artificial Intelligence (IJCAI)
  • Xu, Lin and Hutter, Frank and Hoos, Holger and Leyton-Brown, Kevin (pdf)(bib)
    Detailed SATzilla Results from the Data Analysis Track of the 2011 SAT Competition
    SAT 2011 Competition, Data Analysis Track, 2011.
  • Hutter, F. and Hoos, H. H. and Leyton-Brown, K. (pdf)(slides)(bib)
    Sequential Model-Based Optimization for General Algorithm Configuration
    In: Proceedings of the conference on Learning and Intelligent OptimizatioN (LION 5)
    Best paper award (second prize).
    SMAC, ROAR, and the instances used are available from the Automated Algorithm Configuration project page.
    An extended version with additional details is available as UBC tech report TR-2010-10. (pdf)(bib)

2010

  • Hutter, F. and Bartz-Beielstein, T. and Hoos, H.H. and Leyton-Brown, K. and Murphy, K.P. (pdf)(bib)
    Sequential Model-Based Parameter Optimisation: an Experimental Investigation of Automated and Interactive Approaches
    In: Empirical Methods for the Analysis of Optimization Algorithms
  • Hutter, Frank and Hoos, Holger H. and Leyton-Brown, Kevin (pdf)(bib)
    Tradeoffs in the Empirical Evaluation of Competing Algorithm Designs
    In: Annals of Mathematics and Artificial Intelligenc (AMAI), Special Issue on Learning and Intelligent Optimization 60.1 (2010): 65--89
    The data from this paper, as well as the empirical analysis tools we introduced are available from the Automated Algorithm Configuration project page.
  • Hutter, F. and Hoos, H. H. and Leyton-Brown, K. (pdf)(slides)(bib)
    Automated Configuration of Mixed Integer Programming Solvers
    In: Proceedings of the Conference on Integration of Artificial Intelligence and Operations Research techniques in Constraint Programming (CPAIOR)
    Our webpage on Automated Configuration of MIP solvers also gives the parameter files for CPLEX, Gurobi, and lpsolve.
  • Hutter, F. and Hoos, H. H. and Leyton-Brown, K. and Murphy, K. P. (pdf)(slides)(bib)
    Time-Bounded Sequential Parameter Optimization
    In: Proceedings of the conference on Learning and Intelligent OptimizatioN (LION 4)
    Runner-up for the best paper award

2009

  • Frank Hutter (pdf)(slides)(bib)
    Automated Configuration of Algorithms for Solving Hard Computational Problems
    PhD thesis, University of British Columbia, Department of Computer Science, Vancouver, Canada
    There are also slides from invited presentation at Canadian AI grad student symposium.
    2010 CAIAC Doctoral Dissertation Award for the best thesis in Artificial Intelligence at a Canadian University completed in 2009.
    See the Automated Algorithm Configuration project page for a lot of experimental data (target algorithms, parameters, benchmark instances, and configuration proceduers).
  • Hutter, Frank and Hoos, Holger H. and Leyton-Brown, Kevin and Stützle, Thomas (pdf)(bib)
    ParamILS: An Automatic Algorithm Configuration Framework
    In: Journal of Artificial Intelligence Research 36 (2009): 267--306
    See the ParamILS project page for a lot of experimental data for this paper (target algorithms, parameters, resulting parameter configurations).
    There's also a quick start guide available to help you apply ParamILS for tuning your own algorithms.
    There's also an older tech report about ParamILS, including additional material (pdf)(bib).
  • Hutter, F. and de Oca, M. A. Montes (pdf)(bib)
    SLS-DS 2009: Doctoral Symposium on Engineering Stochastic Local Search Algorithms
    IRIDIA, Université Libre de Bruxelles, Brussels, Belgium
  • Hutter, F. and Hoos, H. H. and Leyton-Brown, K. and Murphy, K. P. (pdf)(bib)
    An Experimental Investigation of Model-Based Parameter Optimisation: SPO and Beyond
    In: Proceedings of the 11th annual conference on Genetic and evolutionary computation (GECCO '09)
  • Lin Xu and Frank Hutter and Holger Hoos and Kevin Leyton-Brown (pdf)(bib)
    SATzilla2009: an Automatic Algorithm Portfolio for SAT
    Solver description, SAT competition 2009
    Solver description for the 2009 SAT competition. SATzilla2009 won 3 gold and 2 silver medals in that competition. See the SATzilla project page for details and source code.

2008

  • Xu, Lin and Hutter, Frank and Hoos, Holger H. and Leyton-Brown, Kevin (pdf)(bib)
    SATzilla: Portfolio-based Algorithm Selection for SAT
    In: Journal of Artificial Intelligence Research 32 (2008): 565--606
    2010 IJCAI/JAIR Best Paper Prize for the period 2005-2009.
    See the SATzilla project page for details and source code.

2007

  • Hutter, Frank and Babic, Domagoj and Hoos, Holger H. and Hu, Alan J. (pdf)(bib)
    Boosting Verification by Automatic Tuning of Decision Proceedingsdures
    In: Proceedings of Formal Methods in Computer Aided Design (FMCAD'07)
    With the tuning discussed in this paper Domagoj's solver Spear won the QF_BV (Quantifier-Free Bit Vector) category of the 2007 Satisfiability Modulo Theories Competition.
  • Hutter, Frank (pdf)(bib)
    On the Potential of Automatic Algorithm Configuration
    In: Proceedings of the Doctoral Symposium on Engineering Stochastic Local Search Algorithms (SLS-DS).
    Best poster award (voted by the attendees of SLS 07).
  • Lin Xu and Frank Hutter and Holger H. Hoos and Kevin Leyton-Brown (pdf)(bib)
    SATzilla-07: The Design and Analysis of an Algorithm Portfolio for SAT
    In: Principles and Practice of Constraint Programming (CP'07)
    SATzilla won 3 gold medals, 1 silver and 1 bronze in the 2007 SAT competition! It is available for download from the SATzilla website.
  • Frank Hutter and Holger H. Hoos and Thomas Stützle (pdf)(slides)(bib)
    Automatic Algorithm Configuration based on Local Search
    In: Proceedings of the Twenty-Second Conference on Artifical Intelligence (AAAI '07)
    The ParamILS algorithm introduced in this paper is available for download from the . There's also a quick start guide available to help you apply it for tuning your own algorithms.
  • Tompkins, Dave and Hutter, Frank and and Hoos, Holger H. (pdf)(bib)
    Scaling and Probabilistic Smoothing (SAPS)
    Solver description from the SAT competition 2007
    SAPS is unchanged from last year, but I got a tenfold speedup by automated parameter tuning (using the techniques from the AAAI-07 ParamILS paper)
  • Xu, Lin and Hutter, Frank and Hoos, Holger H. and Leyton-brown, Kevin (pdf)(bib)
    SATzilla2007: a new & improved algorithm portfolio for SAT
    Solver description from the SAT competition 2007
    In a nutshell, SATzilla predicts the runtime of each solver in the portfolio and picks the most promising one.
    SATzilla2007 won 3 gold medals, 1 silver and 1 bronze! See the SAT competition webpage for details.
  • Domagoj Babić and Frank Hutter (pdf)(bib)
    SPEAR Theorem Prover
    Solver description from the SAT competition 2007
    SPEAR is a new tree search algorithm with 25 free parameters. I tuned it (using the techniques from the AAAI-07 paper on ParamILS), getting a 30% speedup; for software verification, my parameter settings beat the default by a factor of 50!

2006

  • Frank Hutter and Youssef Hamadi and Holger H. Hoos and Kevin Leyton-Brown (pdf)(ppt)(bib)
    Performance Prediction and Automated Tuning of Randomized and Parametric Algorithms
    In: Principles and Practice of Constraint Programming (CP'06)
    All our experimental data for this paper, as well as our Matlab code, is available on the Empirical Hardness Models project page.
  • Hutter, Frank and Ruml, Wheeler (bib)
    Learning for Search: Papers from the 2006 AAAI Workshop
    Proceedings of the AAAI 06 workshop on Learning for Search
  • Hutter, Frank (bib)
    Automated Algorithm Configuration Based on Machine Learning
    PhD proposal, Department of Computer Science, University of British Columbia

2005

2004

  • Hutter, Frank (pdf)(bib)
    Stochastic Local Search for Solving the Most Probable Explanation Problem in Bayesian Networks
    MSc thesis, Darmstadt University of Technoloy
    Supervisor: Thomas Stützle, Cosupervisor: Holger Hoos; My solver GLS+ and most of the test instances I used are available on our MPE page.
  • Hutter, Frank and Ng, Brenda and Dearden, Richard (pdf)(bib)
    Incremental Thin Junction Trees for Dynamic Bayesian Networks
    Techreport TR-AIDA-04-01, Intellectics Group, Darmstadt University of Technology
  • de Freitas, Nando and Dearden, Richard and Hutter, Frank and Morales-Menendez, Ruben and Mutch, Jim and Poole, David (pdf)(bib)
    Diagnosis by a Waiter and a Mars Explorer
    In: Proceedings of the IEEE 92.4 (2004): 139-144
    Check out my GPF webpage for the particle filtering code used for the rover examples.
  • Dearden, Richard and Willeke, Thomas and Hutter, Frank and Simmons, Reid and Verma, Vandi and Thrun, Sebastian (pdf)(bib)
    Real-time Fault Detection and Situational Awareness for Rovers: Report on the Mars Technology Program Task
    In: In Proceedings of IEEE Aerospace Conference, 2004
    Check out my GPF webpage for the particle filtering code.
  • Andronescu, M. and Fejes, A. P. and Hutter, F. and Hoos, H. H. and Condon, A. (pdf)(bib)
    A new algorithm for RNA secondary structure design
    In: Journal of Molecular Biology 336.3 (2004): 607--624
    Check out the free RNA Designer Software at http://www.rnasoft.ca/

2003

  • Hutter, Frank and Dearden, Richard (pdf)(bib)
    The Gaussian Particle Filter for Diagnosis of Non-Linear Systems
    In: Proceedings of the 14th International Conference on Principles of Diagnosis(DX03)
    Check out my GPF webpage for the Gaussian particle filtering code.
  • Hutter, Frank and Dearden, Richard (pdf)(bib)
    Efficient On-line Fault Diagnosis for Non-Linear Systems
    In: Seventh International Symposium on Artificial Intelligence and Robotics in Space (i-SAIRAS-03)
    Check out my GPF webpage for the Gaussian particle filtering code.

2002

  • Frank Hutter and Dave A.D. Tompkins and Holger H. Hoos (pdf)(bib)
    Scaling and Probabilistic Smoothing: Efficient Dynamic Local Search for SAT
    In: Principles and Practice of Constraint Programming - CP 2002
    Check out the DLS for SAT webpage, maintained by Dave.
  • Andronescu, M. and Fejes, A. P. and Hutter, F. and Hoos, H. H. and Condon, A. (bib)
    A New SLS Algorithm for RNA Secondary Structure Design
    Techreport TR-2002-10, Department of Computer Science, University of British Columbia
    Available as a postscript file.
    Check out the free RNA Designer Software at http://www.rnasoft.ca/