Presents a robust algorithm for linear dueling bandits that achieves delay-regime-agnostic regret of order d(sqrt(T) + C + D) with additive costs for corruption and delay under post-serving contexts.
Feel-good thompson sam- pling for contextual dueling bandits.arXiv preprint arXiv:2404.06013
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3verdicts
UNVERDICTED 3representative 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.
Variance-aware neural dueling bandit algorithms achieve sublinear regret of order O(d sqrt(sum sigma_t^2) + sqrt(d T)) for wide networks on nonlinear utilities.
citing papers explorer
-
Robust Linear Dueling Bandits with Post-serving Context under Unknown Delays and Adversarial Corruptions
Presents a robust algorithm for linear dueling bandits that achieves delay-regime-agnostic regret of order d(sqrt(T) + C + D) with additive costs for corruption and delay under post-serving contexts.
-
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.
-
Neural Variance-aware Dueling Bandits with Deep Representation and Shallow Exploration
Variance-aware neural dueling bandit algorithms achieve sublinear regret of order O(d sqrt(sum sigma_t^2) + sqrt(d T)) for wide networks on nonlinear utilities.