Holger H. Hoos
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Holger H. Hoos has a total of 275 co-authors. Here are the top co-authors by number of shared publications:
- Kevin Leyton-Brown
Department of Computer Science University of British Columbia
20 shared publications - Thomas Stützle
Universite Libre de Bruxelles
15 shared publications - Marius Lindauer
Leibniz University Hannover
11 shared publications Frank Hutter
University of Freiburg
8 shared publications- Frank Hutter
Department of Computer Science University of British Columbia 201-2366 Main Mall V6T 1Z4 BC CANADA
8 shared publications - Jan N. van Rijn
Leiden University, Leiden, The Netherlands
8 shared publications
Latest Publications
- Open Access
- 25 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computing for Healthcare
The Challenge of Multi-Organ Crosstalk Research
The prevalence of multimorbid patients (i.e., one person with two or more diseases) is critical for patients, medical doctors, and society alike since it complicates treatment and results in high (treatment) costs. However, contemporary medicine mainly specializes in single-organ approaches, frequently overlooking the interactions between different organs causing multimorbidities. Recent research on bilateral organ crosstalk (OCT) reveals the complex interplay between organs and the importance of studying OCT, especially involving more than two organs. Tackling the challenges associated with multi-organ crosstalk requires fundamental methodological advances in computer science, specifically related to handling multi-modal data, the combinatorial explosion of complexity, and data sensitivity. Thus, research should generally be directed toward (i) methods for identifying affected organs, (ii) concepts for discovering disease progression, and (iii) models for validation in clinical studies. When addressing these challenges interdisciplinarily, computer science and medicine will jointly improve the understanding of OCT and multimorbidity, resulting in novel treatment options for multimorbid patients, reduced healthcare costs, and broad benefits for society.
- 25 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computing for Healthcare
Open AccessThe Challenge of Multi-Organ Crosstalk Research
The prevalence of multimorbid patients (i.e., one person with two or more diseases) is critical for patients, medical doctors, and society alike since it complicates treatment and results in high (treatment) costs. However, contemporary medicine mainly specializes in single-organ approaches, frequently overlooking the interactions between different organs causing multimorbidities. Recent research on bilateral organ crosstalk (OCT) reveals the complex interplay between organs and the importance of studying OCT, especially involving more than two organs. Tackling the challenges associated with multi-organ crosstalk requires fundamental methodological advances in computer science, specifically related to handling multi-modal data, the combinatorial explosion of complexity, and data sensitivity. Thus, research should generally be directed toward (i) methods for identifying affected organs, (ii) concepts for discovering disease progression, and (iii) models for validation in clinical studies. When addressing these challenges interdisciplinarily, computer science and medicine will jointly improve the understanding of OCT and multimorbidity, resulting in novel treatment options for multimorbid patients, reduced healthcare costs, and broad benefits for society.
- Open Access
- 20 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 179-195
The AI Reproducibility Index: Ranking Venues, Countries and Institutions by Reproducibility
- 20 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 179-195
Open AccessThe AI Reproducibility Index: Ranking Venues, Countries and Institutions by Reproducibility
- Open Access
- 20 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 158-166
Reproducibility of the NeurIPS 2020 Black-Box Optimization Challenge: Re-evaluating Competition Submissions
- 20 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 158-166
Open AccessReproducibility of the NeurIPS 2020 Black-Box Optimization Challenge: Re-evaluating Competition Submissions
- 18 July 2026
- Published by Springer Nature
- p. 232-253
Automated Algorithm Configuration of $\alpha $, $\beta $-CROWN- 18 July 2026
- Published by Springer Nature
- p. 232-253
Automated Algorithm Configuration of $\alpha $, $\beta $-CROWN- Open Access
- 13 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1260-1264
Improving Evaluation of Recombination-based Cartesian Genetic Programming
- 13 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1260-1264
Open AccessImproving Evaluation of Recombination-based Cartesian Genetic Programming
- Open Access
- 30 June 2026
- Published by SAGE Publications in The European Journal on Artificial Intelligence
Instance Selection Methods in Automated Algorithm Configuration
Empirical performance evaluation is crucial for algorithm configuration and performance optimization. Prior work showed that comparing the running time of two algorithms can be accelerated by evaluating them on strategically selected instances. We explore this approach in the context of automated algorithm configuration, adapting prior methods to leverage empirical performance models and introducing two active learning-inspired methods. We evaluate these methods on two performance comparison situations arising during configuration, achieving speedups of 5 to 3,000 times over the random instance sampling method of state-of-the-art configurators. We then integrate the best methods into the model-based configurator sequential model-based algorithm configurator (SMAC). In two of five running time optimization scenarios, we nearly double the performance gain of SMAC. An ablation study confirms that instance selection drives this improvement, indicating substantial potential for advancing algorithm configuration.
- 30 June 2026
- Published by SAGE Publications in The European Journal on Artificial Intelligence
Open AccessInstance Selection Methods in Automated Algorithm Configuration
Empirical performance evaluation is crucial for algorithm configuration and performance optimization. Prior work showed that comparing the running time of two algorithms can be accelerated by evaluating them on strategically selected instances. We explore this approach in the context of automated algorithm configuration, adapting prior methods to leverage empirical performance models and introducing two active learning-inspired methods. We evaluate these methods on two performance comparison situations arising during configuration, achieving speedups of 5 to 3,000 times over the random instance sampling method of state-of-the-art configurators. We then integrate the best methods into the model-based configurator sequential model-based algorithm configurator (SMAC). In two of five running time optimization scenarios, we nearly double the performance gain of SMAC. An ablation study confirms that instance selection drives this improvement, indicating substantial potential for advancing algorithm configuration.
- 1 May 2026
- Published by Springer Nature
- p. 325-334
Mitigating Representation Bias Caused by Missing Pixels in Methane Plume Detection
- 1 May 2026
- Published by Springer Nature
- p. 325-334
Mitigating Representation Bias Caused by Missing Pixels in Methane Plume Detection
- 1 March 2026
- Published by MIT Press in Evolutionary Computation
- Vol. 34 (1) , 29-52
MO-SMAC: Multiobjective Sequential Model-Based Algorithm Configuration
Automated algorithm configuration aims at finding well-performing parameter configurations for a given problem, and it has proven to be effective within many AI domains, including evolutionary computation. Initially, the focus was on excelling in one performance objective, but, in reality, most tasks have a variety of (conflicting) objectives. The surging demand for trustworthy and resource-efficient AI systems makes this multiobjective perspective even more prevalent. We propose a new general-purpose multiobjective automated algorithm configurator by extending the widely-used SMAC framework. Instead of finding a single configuration, we search for a nondominated set that approximates the actual Pareto set. We propose a pure multiobjective Bayesian optimization approach for obtaining promising configurations by using the predicted hypervolume improvement as acquisition function. We also present a novel intensification procedure to efficiently handle the selection of configurations in a multiobjective context. Our approach is empirically validated and compared across various configuration scenarios in four AI domains, demonstrating superiority over baseline methods, competitiveness with MO-ParamILS on individual scenarios, and an overall best performance.
- 1 March 2026
- Published by MIT Press in Evolutionary Computation
- Vol. 34 (1) , 29-52
MO-SMAC: Multiobjective Sequential Model-Based Algorithm Configuration
Automated algorithm configuration aims at finding well-performing parameter configurations for a given problem, and it has proven to be effective within many AI domains, including evolutionary computation. Initially, the focus was on excelling in one performance objective, but, in reality, most tasks have a variety of (conflicting) objectives. The surging demand for trustworthy and resource-efficient AI systems makes this multiobjective perspective even more prevalent. We propose a new general-purpose multiobjective automated algorithm configurator by extending the widely-used SMAC framework. Instead of finding a single configuration, we search for a nondominated set that approximates the actual Pareto set. We propose a pure multiobjective Bayesian optimization approach for obtaining promising configurations by using the predicted hypervolume improvement as acquisition function. We also present a novel intensification procedure to efficiently handle the selection of configurations in a multiobjective context. Our approach is empirically validated and compared across various configuration scenarios in four AI domains, demonstrating superiority over baseline methods, competitiveness with MO-ParamILS on individual scenarios, and an overall best performance.
- Open Access
Rapid Augmentations for Time Series (RATS): A High-Performance Library for Time Series Augmentation
Time series augmentation is critical for training robust deep learning models, particularly in domains where labelled data is scarce and expensive to obtain. However, existing augmentation libraries for time series, mainly written in Python, suffer from performance bottlenecks, where running time grows exponentially as dataset sizes increase -- an aspect limiting their applicability in large-scale, production-grade systems. We introduce RATS (Rapid Augmentations for Time Series), a high-performance library for time series augmentation written in Rust with Python bindings (RATSpy). RATS implements multiple augmentation methods spanning basic transformations, frequency-domain operations and time warping techniques, all accessible through a unified pipeline interface with built-in parallelisation. Comprehensive benchmarking of RATSpy versus a commonly used library (tasug) on 143 datasets demonstrates that RATSpy achieves an average speedup of 74.5\% over tsaug (up to 94.8\% on large datasets), with up to 47.9\% less peak memory usage.
Open AccessRapid Augmentations for Time Series (RATS): A High-Performance Library for Time Series Augmentation
Time series augmentation is critical for training robust deep learning models, particularly in domains where labelled data is scarce and expensive to obtain. However, existing augmentation libraries for time series, mainly written in Python, suffer from performance bottlenecks, where running time grows exponentially as dataset sizes increase -- an aspect limiting their applicability in large-scale, production-grade systems. We introduce RATS (Rapid Augmentations for Time Series), a high-performance library for time series augmentation written in Rust with Python bindings (RATSpy). RATS implements multiple augmentation methods spanning basic transformations, frequency-domain operations and time warping techniques, all accessible through a unified pipeline interface with built-in parallelisation. Comprehensive benchmarking of RATSpy versus a commonly used library (tasug) on 143 datasets demonstrates that RATSpy achieves an average speedup of 74.5\% over tsaug (up to 94.8\% on large datasets), with up to 47.9\% less peak memory usage.