Pith. sign in

Borda Regret Minimization for Generalized Linear Dueling Bandits

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

Dueling bandits are widely used to model preferential feedback prevalent in many applications such as recommendation systems and ranking. In this paper, we study the Borda regret minimization problem for dueling bandits, which aims to identify the item with the highest Borda score while minimizing the cumulative regret. We propose a rich class of generalized linear dueling bandit models, which cover many existing models. We first prove a regret lower bound of order $\Omega(d^{2/3} T^{2/3})$ for the Borda regret minimization problem, where $d$ is the dimension of contextual vectors and $T$ is the time horizon. To attain this lower bound, we propose an explore-then-commit type algorithm for the stochastic setting, which has a nearly matching regret upper bound $\tilde{O}(d^{2/3} T^{2/3})$. We also propose an EXP3-type algorithm for the adversarial linear setting, where the underlying model parameter can change at each round. Our algorithm achieves an $\tilde{O}(d^{2/3} T^{2/3})$ regret, which is also optimal. Empirical evaluations on both synthetic data and a simulated real-world environment are conducted to corroborate our theoretical analysis.

fields

cs.AI 1

years

2025 1

verdicts

REJECT 1

representative citing papers

Contextual bandits with entropy-based human feedback

cs.AI · 2025-02-12 · reject · novelty 3.0

An entropy threshold decides when a contextual bandit asks an expert for action recommendations or reward penalties, with improved regret reported on three multi-label datasets.

citing papers explorer

Showing 1 of 1 citing paper.

  • Contextual bandits with entropy-based human feedback cs.AI · 2025-02-12 · reject · none · ref 16 · internal anchor

    An entropy threshold decides when a contextual bandit asks an expert for action recommendations or reward penalties, with improved regret reported on three multi-label datasets.