Skip to yearly menu bar Skip to main content


Learning Tree Structured Potential Games

Vikas Garg · Tommi Jaakkola

Area 5+6+7+8 #46

Keywords: [ Structured Prediction ] [ Game Theory and Econometrics ] [ Model Selection and Structure Learning ]


Many real phenomena, including behaviors, involve strategic interactions that can be learned from data. We focus on learning tree structured potential games where equilibria are represented by local maxima of an underlying potential function. We cast the learning problem within a max margin setting and show that the problem is NP-hard even when the strategic interactions form a tree. We develop a variant of dual decomposition to estimate the underlying game and demonstrate with synthetic and real decision/voting data that the game theoretic perspective (carving out local maxima) enables meaningful recovery.

Live content is unavailable. Log in and register to view live content