Adapting multi-objective pure-exploration bandits enables efficient Pareto prompt set recovery and best feasible prompt identification for LLMs, with linear-case guarantees and empirical gains over baselines.
Constrained pure exploration multi-armed bandits with a fixed budget.arXiv preprint arXiv:2211.14768,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3verdicts
UNVERDICTED 3representative citing papers
Introduces BAI with post-action context in fixed-confidence stochastic bandits, derives instance-dependent lower bounds, and gives asymptotically optimal algorithms for separator and non-separator cases.
A new posterior sampling algorithm for (ε, δ)-PAC policy identification in tabular MDPs achieves asymptotic optimality in sample complexity and posterior contraction rate with O(S²AH) runtime per episode.
citing papers explorer
-
Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits
Adapting multi-objective pure-exploration bandits enables efficient Pareto prompt set recovery and best feasible prompt identification for LLMs, with linear-case guarantees and empirical gains over baselines.
-
Pure Exploration Beyond Reward Feedback: The Role of Post-Action Context
Introduces BAI with post-action context in fixed-confidence stochastic bandits, derives instance-dependent lower bounds, and gives asymptotically optimal algorithms for separator and non-separator cases.
-
Optimal Posterior Sampling for Policy Identification in Tabular Markov Decision Processes
A new posterior sampling algorithm for (ε, δ)-PAC policy identification in tabular MDPs achieves asymptotic optimality in sample complexity and posterior contraction rate with O(S²AH) runtime per episode.