Preselection Bandits
Paper
•
1907.06123
•
Published
Viktor Bengs
BengsV
AI & ML interests
Bandit Algorithms, Uncertainty Quantification, Preference-based Learning, and Explainable AI
Organizations
None yet
authored
12
papers
over 1 year ago
Second-Order Uncertainty Quantification: A Distance-Based Approach
Paper
•
2312.00995
•
Published
Iterative Deepening Hyperband
Paper
•
2302.00511
•
Published
Uniform approximation in classical weak convergence theory
Paper
•
1903.09864
•
Published
Identifying Copeland Winners in Dueling Bandits with Indifferences
Paper
•
2310.00750
•
Published
Non-Stationary Dueling Bandits
Paper
•
2202.00935
•
Published
Finding Optimal Arms in Non-stochastic Combinatorial Bandits with Semi-bandit Feedback and Finite Budget
Paper
•
2202.04487
•
Published
Multi-Armed Bandits with Censored Consumption of Resources
Paper
•
2011.00813
•
Published
Stochastic Contextual Dueling Bandits under Linear Stochastic Transitivity Models
Paper
•
2202.04593
•
Published
Approximating the Shapley Value without Marginal Contributions
Paper
•
2302.00736
•
Published
Pitfalls of Epistemic Uncertainty Quantification through Loss Minimisation
Paper
•
2203.06102
•
Published
On Second-Order Scoring Rules for Epistemic Uncertainty Quantification
Paper
•
2301.12736
•
Published