SupSplitLog achieves Õ(√(dT)) regret for logistic bandits without context diversity assumptions by splitting samples for an initial estimator and Newton correction, and can adapt to data-dependent bounds.
Variance-aware regret bounds for stochastic contextual dueling bandits
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
ActiveDPO is a theoretically grounded active data selection method for sample-efficient LLM alignment that parameterizes the reward model directly with the LLM being aligned.
citing papers explorer
-
Logistic Bandits with $\tilde{O}(\sqrt{dT})$ Regret without Context Diversity Assumptions
SupSplitLog achieves Õ(√(dT)) regret for logistic bandits without context diversity assumptions by splitting samples for an initial estimator and Newton correction, and can adapt to data-dependent bounds.
-
ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment
ActiveDPO is a theoretically grounded active data selection method for sample-efficient LLM alignment that parameterizes the reward model directly with the LLM being aligned.