Mixture Weight Estimation and Model Prediction in Multi-source Multi-target Domain Adaptation

We consider a problem of learning a model from multiple sources with the goal to performwell on a new target distribution. Such problem arises inlearning with data collected from multiple sources (e.g. Thegoal of learner is to mix these data sources in a target-distribution aware way andsimultaneously minimize the empirical risk on the mixed source. The literature has made some tangible advancements in establishingtheory of learning on mixture domain. However, there are still two unsolved problems.