Publications

Thesis

• Bengs, Viktor (2018)
  Confidence sets for change-point problems in nonparametric regression
  Dissertation, Philipps-Universität Marburg
  

top

Journal article

• Haddenhorst, Björn; Bengs, Viktor; Hüllermeier, Eyke (2021)
  On testing transitivity in online preference learning
  In: Machine Learning, Vol. 110, No. 8: pp. 2063-2084 (full text available)
  
• Bengs, Viktor; Busa-Fekete, Róbert; Mesaoudi-Paul, Adil El; Hüllermeier, Eyke (2021)
  Preference-based Online Learning with Dueling Bandits: A Survey
  In: Journal of Machine Learning Research, Vol. 22, No. 7: pp. 1-108 (full text available)
  
• Bengs, Viktor; Holzmann, Hajo (2019)
  Adaptive confidence sets for kink estimation
  In: Electronic Journal of Statistics, Vol. 13, No. 1: pp. 1523-1579 (full text available)
  
• Bengs, Viktor; Eulert, Matthias; Holzmann, Hajo (2019)
  Asymptotic confidence sets for the jump curve in bivariate regression problems
  In: Journal of Multivariate Analysis, Vol. 173: pp. 291-312
  

top

Book Section

• El Mesaoudi-Paul, Adil; Weiß, Dimitri; Bengs, Viktor; Hüllermeier, Eyke; Tierney, Kevin (2020)
  Pool-Based Realtime Algorithm Configuration: A Preselection Bandit Approach
  In: Kotsireas, Ilias S.; Pardalos, Panos M. (eds.): Learning and Intelligent Optimization. 14th International Conference, LION 14, Athens, Greece, May 24–28, 2020, Revised Selected Papers. Lecture Notes in Computer Science; Vol. 12096. Cham: Springer. pp. 216-232
  

top

Conference Item

• Brandt, Jasmin; Wever, Marcel; Bengs, Viktor; Hüllermeier, Eyke (2024)
  Best Arm Identification with Retroactively Increased Sampling Budget for More Resource-Efficient HPO
  Thirty-Third International Joint Conference on Artificial Intelligence (IJCAI-24), 3. - 9. August 2024, Jeju, South Korea
  
• Kaufmann, Timo; Bengs, Viktor; Hüllermeier, Eyke (2024)
  Reinforcement Learning from Human Feedback for Cyber-Physical Systems: On the Potential of Self-Supervised Pretraining
  International Conference on Machine Learning For Cyber-Physical Systems (ML4CPS 2023), 29. - 31. March 2023, Hamburg, Germany (full text available)
  
• Kolpaczki, Patrick; Bengs, Viktor; Muschalik, Maximilian; Hüllermeier, Eyke (2024)
  Approximating the Shapley Value without Marginal Contributions
  AAAI Conference on Artificial Intelligence 2024, 20-27 February 2024, Vancouver, Canada (full text available)
  
• Schede, Elias; Brandt, Jasmin; Tornede, Alexander; Wever, Marcel; Bengs, Viktor; Hüllermeier, Eyke; Tierney, Kevin (2023)
  A Survey of Methods for Automated Algorithm Configuration (Extended Abstract)
  Thirty-Second International Joint Conference on Artificial Intelligence (IJCAI 2023), 19-25 August 2023, Macao, S.A.R
  
• Mortier, Thomas; Bengs, Viktor; Hüllermeier, Eyke; Luca, Stijn; Waegeman, Willem (2023)
  On the Calibration of Probabilistic Classifier Sets
  26th International Conference on Artificial Intelligence and Statistics (AISTATS 2023), 25-27 April, 2023, Valencia, Spain (full text available)
  
• Brandt, Jasmin; Schede, Elias; Haddenhorst, Björn; Bengs, Viktor; Hüllermeier, Eyke; Tierney, Kevin (2023)
  AC-Band: A Combinatorial Bandit-Based Approach to Algorithm Configuration
  AAAI Conference on Artificial Intelligence, February, 2023, Washington, DC, USA (full text available)
  
• Bengs, Viktor; Saha, Aadirupa; Hüllermeier, Eyke (2022)
  Stochastic Contextual Dueling Bandits under Linear Stochastic Transitivity Models
  39th International Conference on Machine Learning, July 17-23 2022, Baltimore, MD, USA (full text available)
  
• Tornede, Alexander; Bengs, Viktor; Hüllermeier, Eyke (2022)
  Machine Learning for Online Algorithm Selection under Censored Feedback
  Thirty-Sixth AAAI Conference on Artificial Intelligence, February 22–March 1, 2022, Virtual
  
• Haddenhorst, Björn; Bengs, Viktor; Hüllermeier, Eyke (2021)
  Identification of the Generalized Condorcet Winner in Multi-dueling Bandits
  Advances in Neural Information Processing Systems, December 7 2021, Virtual (full text available)
  
• Kolpaczki, Patrick; Bengs, Viktor; Hüllermeier, Eyke (2021)
  Identifying Top-k Players in Cooperative Games via Shapley Bandits
  LWDA’21: Lernen, Wissen, Daten, Analysen, 1. - 3. September, 2021, Munich, Germany (full text available)
  
• Haddenhorst, Björn; Bengs, Viktor; Brandt, Jasmin; Hüllermeier, Eyke (2021)
  Testification of Condorcet Winners in dueling bandits
  Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, July 27-30, 2021, Virtual (full text available)
  
• Mohr, Felix; Bengs, Viktor; Hüllermeier, Eyke (2021)
  Single Player Monte-Carlo Tree Search Based on the Plackett-Luce Model
  AAAI Conference on Artificial Intelligence, February 2–9, 2021, Virtual
  
• Bengs, Viktor; Hüllermeier, Eyke (2020)
  Preselection Bandits
  37th International Conference on Machine Learning, July 12-18 2020, Virtual (full text available)
  

top

Other

• Kaufmann, Timo; Weng, Paul; Bengs, Viktor; Hüllermeier, Eyke (2024)
  A Survey of Reinforcement Learning from Human Feedback
  (full text available)