Yurong Chen  陈昱蓉

SELECTED PAPERS

1. ICML

   Coordinated Dynamic Bidding in Repeated Second-Price Auctions with Budgets

   Yurong Chen, Qian Wang, Zhijian Duan, Haoran Sun, Zhaohua Chen, Xiang Yan, and Xiaotie Deng

   In Proceedings of the 40th International Conference on Machine Learning 23–29 jul 2023

   Abs arXiv Bib PDF Poster

   In online ad markets, a rising number of advertisers are employing bidding agencies to participate in ad auctions. These agencies are specialized in designing online algorithms and bidding on behalf of their clients. Typically, an agency usually has information on multiple advertisers, so she can potentially coordinate bids to help her clients achieve higher utilities than those under independent bidding. In this paper, we study coordinated online bidding algorithms in repeated second-price auctions with budgets. We propose algorithms that guarantee every client a higher utility than the best she can get under independent bidding. We show that these algorithms achieve maximal social welfare and discuss bidders’ incentives to misreport their budgets, in symmetric cases. Our proofs combine the techniques of online learning and equilibrium analysis, overcoming the difficulty of competing with a multi-dimensional benchmark. The performance of our algorithms is further evaluated by experiments on both synthetic and real data. To the best of our knowledge, we are the first to consider bidder coordination in online repeated auctions with constraints.

   @inproceedings{chen2023coordinated,
     title = {Coordinated Dynamic Bidding in Repeated Second-Price Auctions with Budgets},
     author = {Chen, Yurong and Wang, Qian and Duan, Zhijian and Sun, Haoran and Chen, Zhaohua and Yan, Xiang and Deng, Xiaotie},
     booktitle = {Proceedings of the 40th International Conference on Machine Learning},
     pages = {5052--5086},
     year = {2023},
     volume = {202},
     series = {Proceedings of Machine Learning Research},
     month = {23--29 Jul},
     publisher = {PMLR},
   }

2. WINE Best Student Paper

   Optimal Private Payoff Manipulation Against Commitment in Extensive-form Games

   ❈ Yurong Chen, Xiaotie Deng, and Yuhao Li

   In Web and Internet Economics 23–29 jul 2022

   Abs arXiv Bib Poster Slides

   To take advantage of strategy commitment, a useful tactic of playing games, a leader must learn enough information about the follower’s payoff function. However, this leaves the follower a chance to provide fake information and influence the final game outcome. Through a carefully contrived payoff function misreported to the learning leader, the follower may induce an outcome that benefits him more, compared to the ones when he truthfully behaves. We study the follower’s optimal manipulation via such strategic behaviors in extensive-form games. Followers’ different attitudes are taken into account. An optimistic follower maximizes his true utility among all game outcomes that can be induced by some payoff function. A pessimistic follower only considers misreporting payoff functions that induce a unique game outcome. For all the settings considered in this paper, we characterize all the possible game outcomes that can be induced successfully. We show that it is polynomial-time tractable for the follower to find the optimal way of misreporting his private payoff information. Our work completely resolves this follower’s optimal manipulation problem on an extensive-form game tree.

   @inproceedings{chen2022optimal,
     author = {Chen, Yurong and Deng, Xiaotie and Li, Yuhao},
     editor = {Hansen, Kristoffer Arnsfelt and Liu, Tracy Xiao and Malekian, Azarakhsh},
     title = {Optimal Private Payoff Manipulation Against Commitment in Extensive-form
                    Games},
     booktitle = {Web and Internet Economics},
     year = {2022},
     publisher = {Springer International Publishing},
     address = {cham},
     pages = {355},
   }

3. Arxiv

   Learning to Manipulate a Commitment Optimizer

   ❈ Yurong Chen, Xiaotie Deng, Jiarui Gan, and Yuhao Li

   23–29 jul 2023

   Abs arXiv Bib

   We consider a Stackelberg scenario where the leader commits optimally based on the follower’s type (i.e., the follower’s payoff function). Despite its rationality, such commitmentoptimizing behavior inadvertently reveals information about the leader’s incentive, especially when one gets access to the leader’s optimal commitments against different follower types. In this paper, we study to what extent one can learn about the leader’s payoff information by actively querying the leader’s optimal commitments. We show that, by using polynomially many queries and operations, a learner can learn a payoff function that is strategically equivalent to the leader’s original payoff function, in the sense that it preserves: 1) the leader’s preference over fairly broad sets of strategy profiles and 2) the set of all possible (strong) Stackelberg equilibria the leader may engage in, considering all possible follower types. As an application, we show that a follower can use the learned information to induce an optimal Stackelberg equilibrium (w.r.t. the follower’s payoff) by imitating a different type, without knowing the leader’s payoff function beforehand. To the best of our knowledge, we are the first to extend this equilibrium inducing problem to the incomplete information setting

   @misc{chen2023learning,
     title = {Learning to Manipulate a Commitment Optimizer},
     author = {Chen, Yurong and Deng, Xiaotie and Gan, Jiarui and Li, Yuhao},
     year = {2023},
     eprint = {2302.11829},
     archiveprefix = {arXiv},
     primaryclass = {cs.GT},
   }

4. Arxiv

   Are Bounded Contracts Learnable and Approximately Optimal?

   ❈ Yurong Chen, Zhaohua Chen, Xiaotie Deng, and Zhiyi Huang

   23–29 jul 2024

   Abs arXiv Bib

   This paper considers the hidden-action model of the principal-agent problem, in which a principal incentivizes an agent to work on a project using a contract. We investigate whether contracts with bounded payments are learnable and approximately optimal. Our main results are two learning algorithms that can find a nearly optimal bounded contract using a polynomial number of queries, under two standard assumptions in the literature: a costlier action for the agent leads to a better outcome distribution for the principal, and the agent’s cost/effort has diminishing returns. Our polynomial query complexity upper bound shows that standard assumptions are sufficient for achieving an exponential improvement upon the known lower bound for general instances. Unlike the existing algorithms which relied on discretizing the contract space, our algorithms directly learn the underlying outcome distributions. As for the approximate optimality of bounded contracts, we find that they could be far from optimal in terms of multiplicative or additive approximation, but satisfy a notion of mixed approximation.

   @misc{chen2024bounded,
     author = {Chen, Yurong and Chen, Zhaohua and Deng, Xiaotie and Huang, Zhiyi},
     year = {2024},
     eprint = {2402.14486},
     archiveprefix = {arXiv},
     primaryclass = {cs.GT},
   }