A Unified Model for the Two-stage Offline-then-Online Resource Allocation

Furthermore, upon the arrival of any online agent, we have to decide quickly and irrevocably which offline agent(s) to With the popularity of the Internet, traditional offline match it with. That is mainly due to the low "patience" of resource allocation has evolved into a new the online agents. These features--online arrivals and the form, called online resource allocation. It features real-time decision-making requirement--distinguish OMMs the online arrivals of agents in the system and the from traditional matching markets where the information of real-time decision-making requirement upon the arrival all agents is fully disclosed in advance. of each online agent. Both offline and online OMMs have received significant interest in both computer resource allocation have wide applications in science and operations research communities. There is a various real-world matching markets ranging from large body of research work who studied matching policy ridesharing to crowdsourcing. There are some design for the profit maximization in ridesharing [Ashlagi emerging applications such as rebalancing in bike et al., 2019; Lowalekar et al., 2018; Bei and Zhang, 2018; sharing and trip-vehicle dispatching in ridesharing, Zhao et al., 2019; Dickerson et al., 2018a; Li et al., 2020], which involve a two-stage resource allocation process.