The next C3.ai Digital Transformation Institute Colloquia on Digital Transformation Science will be Thursday, March 4 at 3:00 p.m. U.S. Central time. Presenting "Beyond Open Loop Thinking: A Prelude to Learning-Based Intelligent Systems" will be Lillian Ratliff from the University of Washington. Registration is required to attend this event.
Abstract: Learning algorithms are increasingly being deployed in a variety of real world systems. A central tenet of present day machine learning is that when it is arduous to model a phenomenon, observations thereof are representative samples from some, perhaps unknown, static or otherwise independent distribution. In the context of systems such as civil infrastructure and other services (e.g., online marketplaces) dependent on its use, there are two central challenges that call into question the integrity of this tenet. First, (supervised) algorithms tend to be trained on past data without considering that the output of the algorithm may change the environment, and hence the data distribution. Second, data used to either train algorithms offline or as input to online decision-making algorithms may be generated by strategic data sources such as human users. Indeed, such data depends on how the algorithm impacts a user’s individual objectives or (perceived) quality of service, which leads to the underlying data distribution being dependent on the output of the algorithm. This begs the question of how learning algorithms can and should be designed taking into consideration this closed-loop interaction with the environment in which they will be deployed. This talk will provide one perspective on designing and analyzing algorithms by modeling the underlying learning task in the language of game theory and control, and using tools from these domains to provide performance guarantees and highlight recent, promising results in this direction.