Learning Theory and Algorithms for Revenue Optimization in Second-Price Auctions with Reserve

Mohri, Mehryar; Medina, Andrés Muñoz

doi:10.48550/arxiv.1310.5665

Cited by 1 publication

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To perform the task of mechanism learning, one could collect historical data including the agent behavior data and the user data in advance, and then optimize the mechanism on these data. In (Zhu et al 2009;Cui et al 2011;Mohri and Medina 2013), the authors assume agents' behaviors or the behavior distribution will not change when the mechanism changes, and apply machine learning techniques to learn the optimal algorithm. However, as mentioned before, the i.i.d.…”

Section: Mechanism Learning Based On Learned Behavior Modelmentioning

confidence: 99%

Mechanism Learning with Mechanism Induced Data

Liu

Chen

Qin

2015

AAAI

View full text Add to dashboard Cite

Machine learning and game theory are two important directions of AI. The former usually assumes data is independent of the models to be learned; the latter usually assumes agents are fully rational. In many modern Internet applications, like sponsored search and crowdsourcing, the two basic assumptions are violated and new challenges are posed to both machine learning and game theory. To better model and study such applications, we need to go beyond conventional machine learning and game theory (mechanism design), and adopt a new approach called mechanism learning with mechanism induced data. Specifically, we propose to learn a behavior model from data to describe how real agents play the complicated game, instead of making the full-rationality assumption. Then we propose to optimize the mechanism by using the learned behavior models to predict the future behaviors of agents in response to the new mechanism. Because the above process couples mechanism learning and behavior learning in a loop, new algorithms and theories are needed to perform the task and guarantee the asymptotical performance. As shown in this paper, there are many interesting research topics along this direction, many of which are still open problems, waiting for researchers in our community to deeply investigate.

show abstract

Section: Mechanism Learning Based On Learned Behavior Modelmentioning

confidence: 99%