Publications

Monographs

  • Bengs, V. (2018). Confidence sets for change-point problems in nonparametric regression. Ph.D. thesis, Philipps-Universität Marburg.

Journal Publications

  • Bengs, V., Eulert, M., and Holzmann, H. (2019). Asymptotic confidence sets for the jump curve in bivariate regression problems. Journal of Multivariate Analysis, 173, 291–312.
  • Bengs, V., and Holzmann, H. (2019). Adaptive confidence sets for kink estimation. Electronic Journal of Statistics, 1, 1523–1579.
  • Bengs, V., Busa-Fekete, R., El Mesaoudi-Paul, A., and Hüllermeier, E. (2021). Preference-based online learning with dueling bandits: A survey. Journal of Machine Learning Research (JMLR), 22(7), 1–108.
  • Haddenhorst, B., Bengs, V., and Hüllermeier, E. (2021). On testing transitivity in online preference learning. Machine Learning, 110, 2063–2084.
  • Schede, E., Brandt, J., Tornede, A., Wever, M., Bengs, V., Hüllermeier, E., and Tierney, K. (2022). A survey of methods for automated algorithm configuration. Journal of Artificial Intelligence Research, 75, 425–487.
  • Bengs, V., and Hüllermeier, E. (2022). Multi-armed bandits with censored consumption of resources. Machine Learning, 112, 217–240.
  • Kolpaczki, P., Bengs, V., and Hüllermeier, E. (2024). Piecewise-stationary dueling bandits. Transactions on Machine Learning Research, 2835-8856.
  • Kaufmann, T., Weng, P., Bengs, V., and Hüllermeier, E. (2023). A survey of reinforcement learning from human feedback. arXiv. Accepted at Transactions on Machine Learning Research.

International Conferences

  • Bengs, V., and Hüllermeier, E. (2020). Preselection bandits. Proceedings of the 37th International Conference on Machine Learning (ICML) in PMLR, 778–787.
  • El Mesaoudi-Paul, A., Weiß, D., Bengs, V., Hüllermeier, E., and Tierney, K. (2020). Pool-based realtime algorithm configuration: A preselection bandit approach. International Conference on Learning and Intelligent Optimization (LION). Springer, Cham, 216–232.
  • Mohr, F., Bengs, V., and Hüllermeier, E. (2021). Single player Monte-Carlo tree search based on the Plackett-Luce model. Proceedings of the AAAI Conference on Artificial Intelligence, 35(14), 12373–12381.
  • Haddenhorst, B., Bengs, V., Brandt, J., and Hüllermeier, E. (2021). Testification of Condorcet winners in dueling bandits. Conference on Uncertainty in Artificial Intelligence (UAI), 1195–1205.
  • Haddenhorst, B., Bengs, V., and Hüllermeier, E. (2021). Identification of the generalized Condorcet winner in multi-dueling bandits. Advances in Neural Information Processing Systems (NeurIPS), 34, 25904–25916.
  • Tornede, A., Bengs, V., and Hüllermeier, E. (2022). Machine learning for online algorithm selection under censored feedback. Proceedings of the AAAI Conference on Artificial Intelligence, 36(9), 10370–10380.
  • Bengs, V., Saha, A., and Hüllermeier, E. (2022). Stochastic contextual dueling bandits under linear stochastic transitivity models. Proceedings of the 39th International Conference on Machine Learning (ICML) in PMLR, 1764–1786.
  • Bengs, V., Hüllermeier, E., and Wageman, W. (2022). Pitfalls of epistemic uncertainty quantification through loss minimisation. NeurIPS, 35, 29205–29216.
  • Brandt, J., Bengs, V., Haddenhorst, B., and Hüllermeier, E. (2022). Finding optimal arms in non-stochastic combinatorial bandits with semi-bandit feedback and finite budget. NeurIPS, 35, 20621–20634.
  • Brandt, J., Schede, E., Bengs, V., Haddenhorst, B., Hüllermeier, E., and Tierney, K. (2023). AC-Band: A combinatorial bandit-based approach to algorithm configuration. Proceedings of the AAAI Conference on Artificial Intelligence, 37(10), 12355–12363.
  • Mortier, T., Bengs, V., Hüllermeier, E., Stijn, L., and Wageman, W. (2023). Calibration of probabilistic classifier sets. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS) in PMLR, 8857–8870.
  • Bengs, V., Hüllermeier, E., and Wageman, W. (2023). On second-order scoring rules for epistemic uncertainty quantification. ICML, PMLR, 2078–2091.
  • Kolpaczki, P., Bengs, V., Muschalik, M., and Hüllermeier, E. (2024). Approximating the Shapley value without marginal contributions. AAAI, 38(12), 13246–13255.
  • Bengs, V., Haddenhorst, B., and Hüllermeier, E. (2024). Identifying Copeland winners in dueling bandits with indifferences. AISTATS in PMLR, 226–234.
  • Brandt, J., Wever, M., Bengs, V., and Hüllermeier, E. (2024). Best arm identification with retroactively increased sampling budget for more resource-efficient HPO. IJCAI, 3742–3750.
  • Sale, Y., Bengs, V., Caprio, M., and Hüllermeier, E. (2024). Second-order uncertainty quantification: A distance-based approach. ICML, PMLR, 43060–43076.
  • Jürgens, M., Bengs, V., Meinert, N., Hüllermeier, E., and Waegeman, W. (2024). Is epistemic uncertainty faithfully represented by second-order empirical risk minimization? ICML, PMLR, 22624–22642.
  • Thies, S. M., Alfaro, J. C.,, and Bengs, V. (2024). MORE–PLR: Multi-output regression employed for partial label ranking. Discovery Science, 401–416.

Workshop Publications

  • Kolpaczki, P., Bengs, V., and Hüllermeier, E. (2021). Identifying the top-k players in cooperative games via Shapley bandits. LWDA 2021.
  • Kaufmann, T., Bengs, V., and Hüllermeier, E. (2023). Reinforcement learning from human feedback for cyber-physical systems: On the potential of self-supervised pretraining. ML4PCS.
  • Becker, P., and Bengs, V. (2023). Shapley-based feature selection for online algorithm selection. DynXAI Workshop at ECML-PKDD 2023.
  • Brandt, J., Schede, E., Shivam, S., Bengs, V., Hüllermeier, E., and Tierney, K. (2023). Contextual preselection methods in pool-based realtime algorithm configuration. LWDA 2023.
  • Yamagata, T., Oberkofler, T., Kaufmann, T., Bengs, V., Hüllermeier, E., and Santos-Rodriguez, R. (2024). Relatively rational: Learning utilities and rationalities jointly from pairwise preferences. ICML 2024 Workshop on Models of Human Feedback for AI Alignment.

Working Papers

  • Thurner, P.W., Haggerty, F., Bengs, V., and Hüllermeier, E. (2023). Party Preference Orders at the German 2021 Federal Election.
  • Jürgens, M., Mortier, T., Hüllermeier, E., Bengs, V.,, and Waegeman, W. (2025). A calibration test for evaluating set-based epistemic uncertainty representations. arXiv.
  • Wang, J., Alfaro, J. C.,, and Bengs, V. (2025). A comparative analysis of rank aggregation methods for the partial label ranking problem. arXiv.

Technical Reports

  • Bengs, V., and Holzmann, H. (2019). Uniform approximation in classical weak convergence theory. arXiv:1903.09864.