About Us

We are generally interested in economics and computation, artificial intelligence, and operations research, specifically including algorithmic game theory, machine learning, social networks, and multiagent and distributed systems. Our current focus is on the price of anarchy, design and analysis of learning algorithms and dynamics in games, markets, and multiagent systems as well as data analysis including but not limited to algorithmic fairness and bias in AI.

Research Field

Algorithmic Game Theory

Theoretical Machine Learning

Multiagent and Distributed Systems

Latest Research

• Profitable Prediction Market Making via No-Regret Learning
  A common goal of a prediction market maker is to upper bound the worst-case loss since it makes sense for a market maker not to lose an arbitrarily large amount of money. Nevertheless, another objective of profit for a market maker has also been considered in some works. None of these previous works on market makers that ensure profit exploits a connection to no-regret online learning. The goal of regret minimization for learners corresponds to the goal of minimizing the… Read more: Profitable Prediction Market Making via No-Regret Learning
• Multiagent Online Learning in Potential Games and Beyond
  Our series of previous work during 2014-2018 positively answers one of the questions in multiagent online learning: in “which classes of games” would “which kinds of no-regret learning algorithms” strengthen the convergence results? Our previous results confirmed that a large class of learning algorithms can make the joint strategy profile converge to approximate Wardrop/Nash equilibria, a stricter class than the class of coarse correlated equilibria, and furthermore bounded the price of anarchy. The design of algorithms (particularly, the part for… Read more: Multiagent Online Learning in Potential Games and Beyond
• Alternative privacy-preserving online advertising system
  We propose to extend the data broker system concept and perform empirical experiments and lab experiments using human subjects. Our empirical and lab experiments will test users’ strategies and behavior with respect to their bidding as well as their willingness to share their personal data. For theoretic extension toward more practical online advertising systems, we propose to study online advertising market mechanism design in a repeated setting where users, mediators, and advertisers could be no-regret learners, and ask: how should… Read more: Alternative privacy-preserving online advertising system

Latest News

Location