Seminar: Machine Learning Seminar
Strategic Classification- Learning With Data That `Behaves’
Date:
February,19,2025
Start Time:
11:30 - 12:30
Location:
506, Zisapel Building
Zoom:
Zoom link
Add to:
Lecturer:
Nir Rosenfeld
Research Areas:
| The growing success of machine learning has made it appealing as a tool for informing decisions about humans. But humans are not your conventional input: they have goals, beliefs, and aspirations, and take action to promote their own interests. Given that standard learning methods are not designed to handle inputs that “behave”—a natural question is: how should we design learning systems when we know they will be deployed and used in social settings? As a starting point, I will present the problem of strategic classification, in which users can modify their features (at a cost) in response to a learned classifier to obtain favorable predictions. I will then describe some of our work in this field, demonstrating how even mild forms of strategic behavior can dramatically transform the learning problem. Finally, I will argue for strategic classification as a useful formal framework for reasoning about learning under strategic user behavior in general, and which holds potential for applying more elaborate forms of economic modeling. |
| Nir is an assistant professor of Computer Science at the Technion. Is research lies at the intersection of machine learning and human behavior.
|