Acquiring and Aggregating Information in Societal Contexts

Опубликовано 30 апреля 2018, 18:23

The modern world is full of algorithms that use data to make decisions. The data often come from people; the predictions or decisions often affect people. Yet classically, the study of e.g. learning algorithms does not take into account the behavior or priorities of these participants. So: how does this "societal context" impact the understanding and design of systems that acquire and aggregate information?

This talk will discuss the design of systems that take into account, and indeed leverage, strategic behavior of participants in order to gather information and use it to make inferences, predictions, or decisions. We will break down the kinds of challenges and objectives that arise in these settings and several approaches for overcoming them using tools from game theory as well as machine learning.

See more at microsoft.com/en-us/research/v...