Reinforcement Mechanism Design: With Applications to Dynamic Pricing in Sponsored Search Auctions

Weiran Shen, Binghui Peng, Hanpeng Liu, +7

Proceedings of the AAAI Conference on Artificial Intelligence

Reinforcement Mechanism DesignSponsored Search AuctionsElectronic AuctionDynamic PricingMarket Mechanism +12

Tight competitive ratios of classic matching algorithms in the fully online model

Zhiyi Huang, Binghui Peng, Zhihao Gavin Tang, +3

arXiv (Cornell University)

Mathematical ProgrammingRanking AlgorithmEngineeringGame TheoryComputational Complexity +15

Reinforcement Mechanism Design, with Applications to Dynamic Pricing in Sponsored Search Auctions

Weiran Shen, Binghui Peng, Hanpeng Liu, +7

arXiv (Cornell University)

Artificial IntelligenceElectronic AuctionEngineeringGame TheoryReinforcement Learning (Educational Psychology) +19

Training (Overparametrized) Neural Networks in Near-Linear Time

Jan van den Brand, Binghui Peng, Zhao Song, +1

arXiv (Cornell University)

EngineeringMachine LearningSlow Convergence RateSparse Neural NetworkLoss Function +7

Learning Optimal Strategies to Commit To

Binghui Peng, Weiran Shen, Pingzhong Tang, +1

Proceedings of the AAAI Conference on Artificial Intelligence

Stackelberg GamesEngineeringBehavioral Decision MakingGame TheoryPayoff Matrix +18

Public Goods Games in Directed Networks

Christos H. Papadimitriou, Binghui Peng

EngineeringGame TheoryComputational ComplexityComputational Game TheoryMarket Equilibrium Computation +15

Self-Attention Networks Can Process Bounded Hierarchical Languages

Shunyu Yao, Binghui Peng, Christos H. Papadimitriou, +1

EngineeringNeurolinguisticsShunyu YaoBinghui PengLarge Language Model +16

Adaptive Greedy versus Non-adaptive Greedy for Influence Maximization

Wei Chen, Binghui Peng, Grant Schoenebeck, +1

Journal of Artificial Intelligence Research

EngineeringBehavioral Decision MakingInfluence MaximizationNetwork AnalysisSocial Influence +17

Adaptive Greedy versus Non-Adaptive Greedy for Influence Maximization

Wei Chen, Binghui Peng, Grant Schoenebeck, +1

Proceedings of the AAAI Conference on Artificial Intelligence

Adaptive Influence Maximization with Myopic Feedback

Binghui Peng, Wei Chen

arXiv (Cornell University)

Adaptivity GapNetwork AnalysisSocial InfluenceCommunicationSocial Network +15