Mechanism Design for Resource Allocation - with Applications to Centralized Multi-Commodity Routing

We formulate and study the algorithmic mechanism design problem for a general class of resource allocation settings, where the center redistributes the private resources brought by individuals. Money transfer is forbidden. Distinct from the standard literature, which assumes the amount of resources brought by an individual to be public information, we consider this amount as an agent's private, possibly multidimensional type. Our goal is to design truthful mechanisms that achieve two objectives: maxmin and Pareto efficiency. For each objective, we provide a reduction that converts any optimal algorithm into a strategy-proof mechanism that achieves the same objective. Our reductions do not inspect the input algorithms but only query these algorithms as oracles.