Machine Learning with Limited Supervision: Algorithms and Applications
Abstract
In many real-world scenarios, acquiring labeled training data can be expensive, time-consuming, or even impractical. This motivates the study of learning from limited supervision, where the goal is to design algorithms that can effectively leverage weaker or noisier supervision signals. In this talk, we will explore various approaches for tackling this problem and discuss their applications in different domains, such as natural language processing, computer vision, and social network analysis. We will also highlight the theoretical guarantees and limitations of these methods.
Bio
Maria-Florina Balcan is a Professor of Computer Science at Carnegie Mellon University, where she is affiliated with the Machine Learning Department and the Computer Science Department. She completed her Ph.D. in Computer Science at Carnegie Mellon University in 2008. Balcan's research focuses on machine learning, algorithmic game theory, and computational aspects of economics. Her work has been recognized with several awards, including the Sloan Research Fellowship, the Microsoft Research Faculty Fellowship, and the Presidential Early Career Award for Scientists and Engineers (PECASE).
