Theoretical Models for Learning from Multiple, Heterogenous and Strategic Agents

With the advent of internet enabled hand-held mobile devices, there is a proliferation of user generated data. Often there is a wealth of useful knowledge embedded within this data and machine learning techniques can be used to extract the information. However, as much of this data is user generated, it suffers from subjectivity. Any machine learning techniques used in this context should address the subjectivity in a principled way. We broadly study three problems in the context of learning from multiple agents, (1) Multi-label classification (2) Active Linear Regression (3) Sponsored Search Auctions.