Learning game-theoretic equilibria via query protocols

Query complexity is a very widespread and recurring theme in the analysis of algorithms and computational complexity. Algorithms are assumed to have access to their input data via certain stylised queries, which impose a constraint on the way an algorithm can behave. In the context of computing equilibria of games, this is a relatively recent line of work, which we review here. The talk mostly focuses on the paper Fearnley et al. (Learning equilibria of games via payoff queries. In: Proceedings of the 14th ACM-EC, pp 397–414, 2013)