In this paper, we develop efficient parameterized algorithms for regimes between these two extremes.

To design an efficient intervention, decision-makers need not only to estimate the total effect of the intervention, but also understand the underlying causal mechanisms driving this effect.

Neural Information Processing Systems http://nips.cc/

Thesegames were chosen soastocovertwonatural application domains for EFCE: conflict resolution via a mediator,andbargainingandnegotiation.

We will fix them in the final version.

We consider the problem of a mediator learning to coordinate a group of strategic agents via recommendations of actions to take without knowledge of their underlying utility functions (e.g.

Collaborative machine learning involves training models on data from multiple parties but must incentivize their participation.