6 papers
Combinatorial Allocation Bandits with Nonlinear Arm Utility
Yuki Shibukawa, Koichi Tanaka, Yuta Saito +1
A matching platform is a system that matches participants of different types, such as companies and job-seekers. In such a platform, maximizing matches may concentrate assignments…
Beyond Match Maximization and Fairness: Retention-Optimized Two-Sided Matching
Ren Kishimoto, Rikiya Takehi, Koichi Tanaka +4
On two-sided matching platforms such as online dating and recruiting, recommendation algorithms often aim to maximize the total number of matches. However, this objective creates a…
A General Framework for Off-Policy Learning with Partially-Observed Reward
Rikiya Takehi, Masahiro Asami, Kosuke Kawakami +1
Off-policy learning (OPL) in contextual bandits aims to learn a decision-making policy that maximizes the target rewards by using only historical interaction data collected under p…
Prompt Optimization with Logged Bandit Data
Haruka Kiyohara, Daniel Yiming Cao, Yuta Saito +1
We study how to use naturally available user feedback, such as clicks, to optimize large language model (LLM) pipelines for generating personalized sentences using prompts. Naive a…
Effective Off-Policy Evaluation and Learning in Contextual Combinatorial Bandits
Tatsuhiro Shimizu, Koichi Tanaka, Ren Kishimoto +3
We explore off-policy evaluation and learning (OPE/L) in contextual combinatorial bandits (CCB), where a policy selects a subset in the action space. For example, it might choose a…
Hyperparameter Optimization Can Even be Harmful in Off-Policy Learning and How to Deal with It
Yuta Saito, Masahiro Nomura
There has been a growing interest in off-policy evaluation in the literature such as recommender systems and personalized medicine. We have so far seen significant progress in deve…