Publications

2024

How can we quantify, explain, and apply the uncertainty of complex soil maps predicted with neural networks?

  • Kerstin Rau, Katharina Eggensperger, Frank Schneider, Philipp Hennig, Thomas Scholten

  • In: Science of Total Environment (STOTEN), 2024

[DOI] [URL]

Towards Bandit-based Optimization for Automated Machine Learning

  • Amir Rezaei Balef, Claire Vernade, Katharina Eggensperger

  • In: Workshop on practical ML for limited/low resource settings (PML4LRS) at ICLR'24, 2024

[URL]

Position: Why We Must Rethink Empirical Research in Machine Learning

  • Moritz Herrmann, Julian Lange, Katharina Eggensperger, Giuseppe Casalicchio, Marcel Wever, Matthias Feurer, David Rügamer, Eyke Hüllermeier, Anne-Laure Boulesteix, Bernd Bischl

  • In: International Conference on Machine Learning (ICML'24), 2024

[arXiv]

Towards Quantifying the Effect of Dataset Selection for Benchmarking Tabular Machine Learning Approaches

  • Ravin Kohli, Matthias Feurer, Bernd Bischl, Katharina Eggensperger, Frank Hutter

  • In: Data-centric Machine Learning Research (DMLR) workshop at ICLR'24, 2024

[URL]

Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoML

  • Hilde Weerts, Florian Pfisterer, Matthias Feurer, Katharina Eggensperger, Noor Awad, Joaquin Vanschoren, Mykola Pechenizkiy, Bernd Bischl, Frank Hutter

  • In: Journal of Artificial Intelligence (JAIR), 2024

[arXiv] [DOI] [URL]

2023

Mind the Gap: Measuring Generalization Performance Across Multiple Objectives

  • Matthias Feurer, Katharina Eggensperger, Edward Bergman, Florian Pfisterer, Bernd Bischl, Frank Hutter

  • In: Proceedings of the Symposium on Intelligen Data Analysis (IDA'23), 2023

[arXiv] [Code] [DOI]

TabPFN: A Transformer that Solves Small Tabular Classification Problems in a Second

  • Noah Hollmann, Samuel Müller, Katharina Eggensperger, Frank Hutter

  • In: International Conference of Learning Representations (ICLR'23), 2023

Note: Superseding “TabPFN: A Transformer that Solves Small Tabular Classification Problems in a Second” in TLR @ NeurIPS 2022

[arXiv] [Code] [URL]

2022

TabPFN: A Transformer that Solves Small Tabular Classification Problems in a Second

  • Noah Hollmann, Samuel Müller, Katharina Eggensperger, Frank Hutter

  • In: NeurIPS Workshop on Table Representation Learning (TRL'22), 2022

Received the best paper award

[arXiv] [Code] [URL] [Video]

SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization

  • Marius Lindauer, Katharina Eggensperger, Matthias Feurer, André Biedenkapp, Difan Deng, Carolin Benjamins, Tim Ruhkopf, René Sass, Frank Hutter

  • In: Journal of Machine Learning (JMLR) -- MLOSS, 2022

[arXiv] [Code] [URL]

Auto-Sklearn 2.0: Hands-free AutoML via Meta-Learning

  • Matthias Feurer, Katharina Eggensperger, Stefan Falkner, Marius Lindauer, Frank Hutter

  • In: Journal of Machine Learning Research (JMLR), 2022

[arXiv] [Code] [URL]

Advanced Hyperparameter Optimization: Performance Modelling and Efficient Benchmarking

  • Katharina Eggensperger

  • In: University of Freiburg, Department of Computer Science, 2022

[URL]

2021

HPOBench: A Collection of Reproducible Multi-Fidelity Benchmark Problems for HPO

  • Katharina Eggensperger, Philipp Müller, Neeratyoy Mallik, Matthias Feurer, René Sass, Aaron Klein, Noor Awad, Marius Lindauer, Frank Hutter

  • In: Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS'21), 2021

[arXiv] [Code] [Slides] [Poster] [URL] [Video]

2020

Squirrel: A Switching Hyperparameter Optimizer Description of the Entry by AutoML.org & IOHProfiler to the NeurIPS 2020 BBO Challenge

  • Noor Awad, Gresa Shala, Difan Deng, Neeratyoy Mallik, Matthias Feurer, Katharina Eggensperger, André Biedenkapp, Diederick Vermetten, Hao Wang, Carola Doerr, Marius Lindauer, Frank Hutter

  • In: arXiv:2012.08180 [cs.LG], 2020

Optimizer description for the NeurIPS 2020 BBO competition. Squirrel won the competition´s warm-starting friendly leaderboard

[arXiv] [Code]

Neural Model-based Optimization with Right-Censored Observations

  • Katharina Eggensperger, Kai Haase, Philipp Müller, Marius Lindauer, Frank Hutter

  • In: arXiv:2009.13828 [cs.AI], 2020

[arXiv]

2019

BOAH: A Tool Suite for Multi-Fidelity Bayesian Optimization and Analysis of Hyperparameters

  • Marius Lindauer, Katharina Eggensperger, Matthias Feurer, André Biedenkapp, Joshua Marben, Philipp Müller, Frank Hutter

  • In: arXiv:1908.06756 [cs.LG], 2019

[arXiv] [Code]

Pitfalls and Best Practices in Algoritm Configuration

  • Katharina Eggensperger, Marius Lindauer, Frank Hutter

  • In: Journal of Artificial Intelligence (JAIR), 2019

[arXiv] [DOI]

Towards Assessing the Impact of Bayesian Optimization’s Own Hyperparameter

  • Marius Lindauer, Matthias Feurer, Katharina Eggensperger, André Biedenkapp, Frank Hutter

  • In: IJCAI Workshop on Data Science meets Optimisatio (DSO'10), 2019

[arXiv] [Slides]

Auto-Sklearn: Efficient and Robust Automated Machine Learning

  • Matthias Feurer, Aaron Klein, Katharina Eggensperger, J. Tobias Springenberg, Manuel Blum, Frank Hutter

  • In: AutoML: Methods, Systems, Challenges, 2019

Adapted version of the 2015 NeurIPS paper “Efficient and Robust Automated Machine Learning

[arXiv] [Code] [DOI] [URL]

2018

Efficient Benchmarking of Algorithm Configurators via Model-Based Surrogates

  • Katharina Eggensperger, Marius Lindauer, Holger H. Hoos, Frank Hutter, Kevin Leyton-Brown

  • In: Machine Learning (MLJ), 2018

[arXiv] [URL]

Neural Networks for Predicting Algorithm Runtime Distribution

  • Katharina Eggensperger, Marius Lindauer, Frank Hutter

  • In: Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI'18), 2018

[arXiv] [Slides] [Poster] [DOI] [URL]

Practical Automated Machine Learning for the AutoML Challenger 2018

  • Matthias Feurer, Katharina Eggensperger, Stefan Falkner, Marius Lindauer, Frank Hutter

  • In: ICML Workshop on Automated Machine Learning (AutoML'18), 2018

[PDF]

2017

Deep Learning with Convolutional Neural Networks for EEG Decoding and Visualization

  • Robin Schirrmeister, J. Tobias Springenberg, Lukas Fiederer, Martin Glasstetter, Katharina Eggensperger, Michael Tangermann, Frank Hutter, Wolfram Burgard, Tonio Ball

  • In: Human Brain Mapping, 2017

[arXiv] [DOI] [URL]

Filtering Outlier in Bayesian Optimization

  • Ruben Martinez-Cantin, Kevin Tee, Mike McCourt, Katharina Eggensperger

  • In: NeurIPS Workshop on Bayesian Optimization (BayesOpt'17), 2017

[Poster] [PDF] [Supp]

Efficient Parameter Importance Analysis via Ablation with Surrogates

  • André Biedenkapp, Marius Lindauer, Katharina Eggensperger, Chris Fawcett, Holger H. Hoos, Frank Hutter

  • In: Proceedings of the Thirty-First Conference on Artificial Intelligence (AAAI'17), 2017

[Code] [Poster] [DOI] [URL] [PDF]

2016

Hyperparameter Optimization for Machine Learning Problems in BCI (Abstract)

  • Andreas Meinel, Katharina Eggensperger, Michael Tangermann, Frank Hutter

  • In: Proceedings of the International Brain Computer Interface Meeting, 2016

[PDF]

2015

Automatic Bone Estimation for Skeleton Tracking in Optical Motion Capture

  • Tobias Schubert, Katharina Eggensperger, Alexis Gkogkidis, Frank Hutter, Tonio Ball, Wolfram Burgard

  • In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA'16), 2015

video showing the results of the optimization procedure

[URL] [PDF]

Efficient and Robust Automated Machine Learning

  • Matthias Feurer, Aaron Klein, Katharina Eggensperger, J. Tobias Springenberg, Manuel Blum, Frank Hutter

  • In: Advances in Neural Information Processing Systems 28 (NeurIPS'15), 2015

[Code] [Poster] [URL]

Methods for Improving Bayesian Optimization for AutoML

  • Matthias Feurer, Aaron Klein, Katharina Eggensperger, J. Tobias Springenberg, Manuel Blum, Frank Hutter

  • In: ICML Workshop on Automated Machine Learning (AutoML'15), 2015

[Slides] [Poster] [PDF]

Efficient Benchmarking of Hyperparameter Optimizers via Surrogates

  • Katharina Eggensperger, Frank Hutter, Holger H. Hoos, Kevin Leyton-Brown

  • In: Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI'15), 2015

Note: Superseding “Surrogate Benchmarks for Hyperparameter Optimization” in MetaSel @ ECAI 2014

[arXiv] [Poster] [DOI] [PDF]

2014

Surrogate Benchmarks for Hyperparameter Optimization

  • Katharina Eggensperger, Frank Hutter, Holger H. Hoos, Kevin Leyton-Brown

  • In: ECAI workshop on Metalearning and Algoritmm Selection (MetaSel'14), 2014

Note: Superseded by “Efficient Benchmarking of Hyperparameter Optimizers via Surrogates” in AAAI 2015

[Slides] [PDF]

2013

Towards an Empirical Foundation for Assessing Bayesian Optimization of Hyperparameters

  • Katharina Eggensperger, Matthias Feurer, Frank Hutter, James Bergstra, Jasper Snoek, Holger H. Hoos, Kevin Leyton-Brown

  • In: NeurIPS workshon on Bayesian Optimization in Theory and Practice (BayesOpt'13), 2013

[Code] [Poster] [PDF]