The K-armed Dueling Bandits Problem

No abstract is available for this paper.

• Publication year

  2012

• Venue

  Annual Conference Computational Learning Theory

• Publication date

  2012-09-01

• Fields of study

  Mathematics, Computer Science

• Identifiers
  DOI 10.1016/J.JCSS.2011.12.028
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Discovery of optimal factors in binary data via a novel method of matrix decomposition

  2010cited by this paper
• Regret bounds for sleeping experts and bandits

  2010cited by this paper
• On the local optimality of LambdaRank

  2009cited by this paper
• Interactively optimizing information retrieval systems as a dueling bandits problem

  2009cited by this paper
• Minimax Policies for Adversarial and Stochastic Bandits

  2009cited by this paper
• The Bayesian Learner is Optimal for Noisy Binary Search  (and Pretty Good for Quantum as Well)

  2008cited by this paper
• How does clickthrough data reflect retrieval quality?

  2008cited by this paper
• Noisy binary search and its applications

  2007influential reference
• The Epoch-Greedy algorithm for contextual multi-armed bandits

  2007cited by this paper
• An Efficient Reduction of Ranking to Classification

  2007cited by this paper
• Bandits for Taxonomies: A Model-based Approach

  2007cited by this paper
• Boosting the Area under the ROC Curve

  2007cited by this paper
• Regret Minimization Under Partial Monitoring

  2006cited by this paper
• Action Elimination and Stopping Conditions for the Multi-Armed Bandit and Reinforcement Learning Problems

  2006cited by this paper
• Robust Reductions from Ranking to Classification

  2006cited by this paper
• Elements of Information Theory

  2005cited by this paper
• A support vector method for multivariate performance measures

  2005cited by this paper
• The Sample Complexity of Exploration in the Multi-Armed Bandit Problem

  2004cited by this paper
• Using Confidence Bounds for Exploitation-Exploration Trade-offs

  2003cited by this paper
• Finite-time Analysis of the Multiarmed Bandit Problem

  2002cited by this paper
• The Nonstochastic Multiarmed Bandit Problem

  2002cited by this paper
• Support vector learning for ordinal regression

  1999cited by this paper
• An Efficient Boosting Algorithm for Combining Preferences

  1998cited by this paper
• Learning to Order Things

  1997cited by this paper
• Randomized Algorithms: Tail Inequalities

  1995cited by this paper
• Probability Inequalities for Sums of Bounded Random Variables

  1994cited by this paper
• Computing with Noisy Information

  1994cited by this paper
• Selection in the presence of noise: the design of playoff systems

  1994cited by this paper
• Some aspects of the sequential design of experiments

  1952cited by this paper
• Asymptotically Efficient Adaptive Allocation Rules

  year unknowncited by this paper

• PARWiS: Winner determination under shoestring budgets using active pairwise comparisons

  2026cites this paper
• GOPO: Policy Optimization using Ranked Rewards

  2026cites this paper
• Back to Blackwell: Closing the Loop on Intransitivity in Multi-Objective Preference Fine-Tuning

  2026cites this paper
• Duel-Evolve: Reward-Free Test-Time Scaling via LLM Self-Preferences

  2026cites this paper
• Active Evaluation of General Agents: Problem Definition and Comparison of Baseline Algorithms

  2026cites this paper
• Learning in Context, Guided by Choice: A Reward-Free Paradigm for Reinforcement Learning with Transformers

  2026influential citation
• What Does Preference Learning Recover from Pairwise Comparison Data?

  2026cites this paper
• Bandit Learning in Matching Markets with Relative Feedback

  2026cites this paper
• Almost Asymptotically Optimal Active Clustering Through Pairwise Observations

  2026cites this paper
• CAPO: Towards Enhancing LLM Reasoning through Generative Credit Assignment

  2025cites this paper
• Neural Constrained Combinatorial Bandits

  2025cites this paper
• Recycling History: Efficient Recommendations from Contextual Dueling Bandits

  2025cites this paper
• Quantum Lipschitz Bandits

  2025cites this paper
• Set It and Forget It: Zero-Mod ML Magic for Linux Tuning

  2025cites this paper
• Adaptive Sample Scheduling for Direct Preference Optimization

  2025cites this paper
• Online Mixture of Experts: No-Regret Learning for Optimal Collective Decision-Making

  2025cites this paper
• Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning

  2025cites this paper
• Toward Efficient Exploration by Large Language Model Agents

  2025cites this paper
• Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds

  2025cites this paper
• Sample Complexity of Identifying the Nonredundancy of Nontransitive Games in Dueling Bandits

  2025cites this paper
• Achieving Nearly-Optimal Regret and Sample Complexity in Dueling Bandits with Applications in Online Recommendations

  2025cites this paper
• HARE: Human-in-the-Loop Algorithmic Recourse

  2025cites this paper
• Efficient Preference-Based Reinforcement Learning: Randomized Exploration Meets Experimental Design

  2025cites this paper
• Fair routing in MoE for distributed spatial data: a combinatorial multi-armed bandit solution

  2025cites this paper
• Cost-Aware Optimal Pairwise Pure Exploration

  2025cites this paper
• Ranking with Multiple Oracles: From Weak to Strong Stochastic Transitivity

  2025cites this paper
• HF-RAG: Hierarchical Fusion-based RAG with Multiple Sources and Rankers

  2025cites this paper
• Preference-based Reinforcement Learning beyond Pairwise Comparisons: Benefits of Multiple Options

  2025cites this paper
• Avoiding $\mathbf{exp(R_{max})}$ scaling in RLHF through Preference-based Exploration

  2025cites this paper
• FedPOB: Sample-Efficient Federated Prompt Optimization via Bandits

  2025cites this paper
• Online Clustering of Dueling Bandits

  2025cites this paper
• Instance-Dependent Regret Bounds for Learning Two-Player Zero-Sum Games with Bandit Feedback

  2025cites this paper
• PrefPaint: Enhancing Image Inpainting through Expert Human Feedback

  2025cites this paper
• CAPO: Towards Enhancing LLM Reasoning through Verifiable Generative Credit Assignment

  2025cites this paper
• Towards a Sharp Analysis of Offline Policy Learning for $f$-Divergence-Regularized Contextual Bandits

  2025cites this paper
• Logarithmic Regret for Online KL-Regularized Reinforcement Learning

  2025cites this paper
• Clustering Items through Bandit Feedback: Finding the Right Feature out of Many

  2025cites this paper
• Neural Variance-aware Dueling Bandits with Deep Representation and Shallow Exploration

  2025cites this paper
• Preference Learning with Response Time

  2025cites this paper
• Accelerating Nash Learning from Human Feedback via Mirror Prox

  2025cites this paper
• Finally Rank-Breaking Conquers MNL Bandits: Optimal and Efficient Algorithms for MNL Assortment

  2025cites this paper
• Continuum-armed Bandit Optimization with Batch Pairwise Comparison Oracles

  2025cites this paper
• Active Human Feedback Collection via Neural Contextual Dueling Bandits

  2025cites this paper
• Fusing Reward and Dueling Feedback in Stochastic Bandits

  2025cites this paper
• ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment

  2025cites this paper
• Knowledge Gradient Procedure to Select the Best System Under Pairwise Comparisons

  2025cites this paper
• Combinatorial Optimization using Comparison Oracles

  2025cites this paper
• Offline Clustering of Preference Learning with Active-data Augmentation

  2025cites this paper
• Constrained Dueling Bandits for Edge Intelligence

  2025cites this paper
• Thompson Sampling in Online RLHF with General Function Approximation

  2025cites this paper
• Inference-Time Personalized Alignment with a Few User Preference Queries

  2025cites this paper
• Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimization

  2025cites this paper
• Feel-Good Thompson Sampling for Contextual Bandits: a Markov Chain Monte Carlo Showdown

  2025cites this paper
• Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective

  2025cites this paper
• Federated Linear Dueling Bandits

  2025cites this paper
• BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning

  2025cites this paper
• Leveraging Sparsity for Sample-Efficient Preference Learning: A Theoretical Perspective

  2025cites this paper
• Embedding the Teacher: Distilling vLLM Preferences for Scalable Image Retrieval

  2025cites this paper
• DP-Dueling: Learning from Preference Feedback without Compromising User Privacy

  2024cites this paper
• Feel-Good Thompson Sampling for Contextual Dueling Bandits

  2024cites this paper
• Non-Stationary Dueling Bandits Under a Weighted Borda Criterion

  2024cites this paper
• Dataset Reset Policy Optimization for RLHF

  2024cites this paper
• Reinforcement Learning from Human Feedback with Active Queries

  2024cites this paper
• Stop Relying on No-Choice and Do not Repeat the Moves: Optimal, Efficient and Practical Algorithms for Assortment Optimization

  2024cites this paper
• Efficient Exploration for LLMs

  2024cites this paper
• Principled Preferential Bayesian Optimization

  2024cites this paper
• Online Iterative Reinforcement Learning from Human Feedback with General Preference Model

  2024cites this paper
• Online Stackelberg Optimization via Nonlinear Control

  2024cites this paper
• Thompson Sampling Procedures for Ranking and Selection with Pairwise Comparisons and Binary Outcomes

  2024cites this paper
• Nearly Optimal Algorithms for Contextual Dueling Bandits from Adversarial Feedback

  2024cites this paper
• A Minimaximalist Approach to Reinforcement Learning from Human Feedback

  2024cites this paper
• Generating Chain-of-Thoughts with a Pairwise-Comparison Approach to Searching for the Most Promising Intermediate Thought

  2024cites this paper
• A Theoretical Analysis of Nash Learning from Human Feedback under General KL-Regularized Preference

  2024cites this paper
• Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF

  2024cites this paper
• Multi-Attribute Optimization Under Preference Uncertainty

  2024cites this paper
• Online Bandit Learning with Offline Preference Data

  2024cites this paper
• Sample-Efficient Alignment for LLMs

  2024cites this paper
• Sharp Analysis for KL-Regularized Contextual Bandits and RLHF

  2024cites this paper
• On Championing Foundation Models: From Explainability to Interpretability

  2024cites this paper
• Prompt Optimization with Human Feedback

  2024cites this paper
• Preferential Multi-Objective Bayesian Optimization

  2024cites this paper
• Unified theory of upper confidence bound policies for bandit problems targeting total reward, maximal reward, and more

  2024cites this paper
• MEReQ: Max-Ent Residual-Q Inverse RL for Sample-Efficient Alignment from Intervention

  2024cites this paper
• DOPL: Direct Online Preference Learning for Restless Bandits with Preference Feedback

  2024cites this paper
• Prompt Optimization with Human Annotations Using Pairwise Comparison

  2024cites this paper
• Optimal Design for Human Feedback

  2024cites this paper
• Multi-Player Approaches for Dueling Bandits

  2024cites this paper
• Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer

  2024cites this paper
• Optimal Design for Reward Modeling in RLHF

  2024cites this paper
• RLHF Workflow: From Reward Modeling to Online RLHF

  2024cites this paper
• Coactive Learning for Large Language Models using Implicit User Feedback

  2024cites this paper
• Adversarial Multi-dueling Bandits

  2024cites this paper
• How to Strategize Human Content Creation in the Era of GenAI?

  2024cites this paper
• Reinforcement Learning from Human Feedback without Reward Inference: Model-Free Algorithm and Instance-Dependent Analysis

  2024cites this paper
• Inverse-Q*: Token Level Reinforcement Learning for Aligning Large Language Models Without Preference Data

  2024cites this paper
• TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correction

  2024cites this paper
• Active Preference Learning for Ordering Items In- and Out-of-sample

  2024cites this paper
• Conversational Dueling Bandits in Generalized Linear Models

  2024cites this paper
• A Graph Theoretic Approach for Preference Learning with Feature Information

  2024cites this paper
• Dissimilarity Bandits

  2024cites this paper