104 citations · 282 across the 16 of their papers we have counts for
18 papers
TACTICL: Task-Aware Compression of Tabular ICL Models
Mykhailo Koshil, Matthias Feurer, Katharina Eggensperger
The strong performance of foundation models for tabular tasks comes at substantial inference costs. Distilling models into task-specific architectures reduces model size and comput…
Best Practices For Empirical Meta-Algorithmic Research: Guidelines from the COSEAL Research Network
Theresa Eimer, Lennart Schäpermeier, André Biedenkapp +15
Empirical research on meta-algorithmics, such as algorithm selection, configuration, and scheduling, often relies on extensive and thus computationally expensive experiments. With…
carps: A Framework for Comparing N Hyperparameter Optimizers on M Benchmarks
Carolin Benjamins, Helena Graf, Sarah Segel +14
Hyperparameter Optimization (HPO) is crucial to develop well-performing machine learning models. In order to ease prototyping and benchmarking of HPO methods, we propose carps, a b…
Position: Why We Must Rethink Empirical Research in Machine Learning
Moritz Herrmann, F. Julian D. Lange, Katharina Eggensperger +7
We warn against a common but incomplete understanding of empirical research in machine learning that leads to non-replicable results, makes findings unreliable, and threatens to un…
Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoML
Hilde Weerts, Florian Pfisterer, Matthias Feurer +7
The field of automated machine learning (AutoML) introduces techniques that automate parts of the development of machine learning (ML) systems, accelerating the process and reducin…
Mind the Gap: Measuring Generalization Performance Across Multiple Objectives
Matthias Feurer, Katharina Eggensperger, Edward Bergman +3
Modern machine learning models are often constructed taking into account multiple objectives, e.g., minimizing inference time while also maximizing accuracy. Multi-objective hyperp…
TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second
Noah Hollmann, Samuel Müller, Katharina Eggensperger +1
We present TabPFN, a trained Transformer that can do supervised classification for small tabular datasets in less than a second, needs no hyperparameter tuning and is competitive w…
SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization
Marius Lindauer, Katharina Eggensperger, Matthias Feurer +6
Algorithm parameters, in particular hyperparameters of machine learning algorithms, can substantially impact their performance. To support users in determining well-performing hype…
HPOBench: A Collection of Reproducible Multi-Fidelity Benchmark Problems for HPO
Katharina Eggensperger, Philipp Müller, Neeratyoy Mallik +6
To achieve peak predictive performance, hyperparameter optimization (HPO) is a crucial component of machine learning and its applications. Over the last years, the number of effici…
Squirrel: A Switching Hyperparameter Optimizer
Noor Awad, Gresa Shala, Difan Deng +9
In this short note, we describe our submission to the NeurIPS 2020 BBO challenge. Motivated by the fact that different optimizers work well on different problems, our approach swit…
Neural Model-based Optimization with Right-Censored Observations
Katharina Eggensperger, Kai Haase, Philipp Müller +2
In many fields of study, we only observe lower bounds on the true response value of some experiments. When fitting a regression model to predict the distribution of the outcomes, w…
Auto-Sklearn 2.0: Hands-free AutoML via Meta-Learning
Matthias Feurer, Katharina Eggensperger, Stefan Falkner +2
Automated Machine Learning (AutoML) supports practitioners and researchers with the tedious task of designing machine learning pipelines and has recently achieved substantial succe…
Towards Assessing the Impact of Bayesian Optimization's Own Hyperparameters
Marius Lindauer, Matthias Feurer, Katharina Eggensperger +2
Bayesian Optimization (BO) is a common approach for hyperparameter optimization (HPO) in automated machine learning. Although it is well-accepted that HPO is crucial to obtain well…
BOAH: A Tool Suite for Multi-Fidelity Bayesian Optimization & Analysis of Hyperparameters
Marius Lindauer, Katharina Eggensperger, Matthias Feurer +4
Hyperparameter optimization and neural architecture search can become prohibitively expensive for regular black-box Bayesian optimization because the training and evaluation of a s…
Neural Networks for Predicting Algorithm Runtime Distributions
Katharina Eggensperger, Marius Lindauer, Frank Hutter
Many state-of-the-art algorithms for solving hard combinatorial problems in artificial intelligence (AI) include elements of stochasticity that lead to high variations in runtime,…
Deep learning with convolutional neural networks for decoding and visualization of EEG pathology
Robin Tibor Schirrmeister, Lukas Gemein, Katharina Eggensperger +2
We apply convolutional neural networks (ConvNets) to the task of distinguishing pathological from normal EEG recordings in the Temple University Hospital EEG Abnormal Corpus. We us…
Pitfalls and Best Practices in Algorithm Configuration
Katharina Eggensperger, Marius Lindauer, Frank Hutter
Good parameter settings are crucial to achieve high performance in many areas of artificial intelligence (AI), such as propositional satisfiability solving, AI planning, scheduling…
Efficient Benchmarking of Algorithm Configuration Procedures via Model-Based Surrogates
Katharina Eggensperger, Marius Lindauer, Holger H. Hoos +2
The optimization of algorithm (hyper-)parameters is crucial for achieving peak performance across a wide range of domains, ranging from deep neural networks to solvers for hard com…