Следене
Viktor Bengs
Viktor Bengs
LMU Munich
Потвърден имейл адрес: lmu.de
Заглавие
Позовавания
Позовавания
Година
A survey of reinforcement learning from human feedback
T Kaufmann, P Weng, V Bengs, E Hüllermeier
arXiv preprint arXiv:2312.14925 10, 2023
1302023
Preference-based online learning with dueling bandits: A survey.
V Bengs, R Busa-Fekete, A El Mesaoudi-Paul, E Hüllermeier
J. Mach. Learn. Res. 22, 7:1-7:108, 2021
1262021
A survey of methods for automated algorithm configuration
E Schede, J Brandt, A Tornede, M Wever, V Bengs, E Hüllermeier, ...
Journal of Artificial Intelligence Research 75, 425-487, 2022
632022
Pitfalls of epistemic uncertainty quantification through loss minimisation
V Bengs, E Hüllermeier, W Waegeman
Advances in Neural Information Processing Systems 35, 29205-29216, 2022
50*2022
On second-order scoring rules for epistemic uncertainty quantification
V Bengs, E Hüllermeier, W Waegeman
International Conference on Machine Learning, 2078-2091, 2023
302023
Approximating the shapley value without marginal contributions
P Kolpaczki, V Bengs, M Muschalik, E Hüllermeier
Proceedings of the AAAI conference on Artificial Intelligence 38 (12), 13246 …, 2024
282024
Stochastic contextual dueling bandits under linear stochastic transitivity models
V Bengs, A Saha, E Hüllermeier
International Conference on Machine Learning, 1764-1786, 2022
282022
Second-order uncertainty quantification: A distance-based approach
Y Sale, V Bengs, M Caprio, E Hüllermeier
arXiv preprint arXiv:2312.00995, 2023
242023
Preselection bandits
V Bengs, E Hüllermeier
International Conference on Machine Learning, 778-787, 2020
15*2020
Finding Optimal Arms in Non-stochastic Combinatorial Bandits with Semi-bandit Feedback and Finite Budget
J Brandt, V Bengs, B Haddenhorst, E Hüllermeier
Advances in Neural Information Processing Systems, 2022
142022
Pool-based realtime algorithm configuration: A preselection bandit approach
A El Mesaoudi-Paul, D Weiß, V Bengs, E Hüllermeier, K Tierney
Learning and Intelligent Optimization: 14th International Conference, LION …, 2020
142020
Uniform approximation in classical weak convergence theory
V Bengs, H Holzmann
arXiv preprint arXiv:1903.09864, 2019
142019
Is epistemic uncertainty faithfully represented by evidential deep learning methods?
M Jürgens, N Meinert, V Bengs, E Hüllermeier, W Waegeman
arXiv preprint arXiv:2402.09056, 2024
102024
Identification of the generalized Condorcet winner in multi-dueling bandits
B Haddenhorst, V Bengs, E Hüllermeier
Advances in Neural Information Processing Systems 34, 25904-25916, 2021
102021
A survey of reinforcement learning from human feedback. arXiv 2023
T Kaufmann, P Weng, V Bengs, E Hüllermeier
arXiv preprint arXiv:2312.14925, 0
9
On the calibration of probabilistic classifier sets
T Mortier, V Bengs, E Hüllermeier, S Luca, W Waegeman
International Conference on Artificial Intelligence and Statistics, 8857-8870, 2023
82023
A survey of reinforcement learning from human feedback (2024)
T Kaufmann, P Weng, V Bengs, E Hüllermeier
URL: https://arxiv. org/abs/2312.14925, 0
8
Non-stationary dueling bandits
P Kolpaczki, V Bengs, E Hüllermeier
arXiv preprint arXiv:2202.00935, 2022
72022
Ac-band: A combinatorial bandit-based approach to algorithm configuration
J Brandt, E Schede, B Haddenhorst, V Bengs, E Hüllermeier, K Tierney
Proceedings of the AAAI Conference on Artificial Intelligence 37 (10), 12355 …, 2023
62023
Machine learning for online algorithm selection under censored feedback
A Tornede, V Bengs, E Hüllermeier
Proceedings of the AAAI Conference on Artificial Intelligence 36 (9), 10370 …, 2022
62022
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–20