IC Colloquium: What Your AI Does Not Know
Event details
| Date | 25.03.2021 |
| Hour | 14:00 › 15:00 |
| Location | Online |
| Category | Conferences - Seminars |
By: Christos Tzamos - University of Wisconsin-Madison
Abstract
As Machine Learning is entering our lives, we are increasingly trusting many important decisions to computer systems. To create reliable and trustworthy technology, computer science must address many outstanding challenges, integrating concepts and ideas from statistics and the social sciences.
In this talk, I will present several contributions of my research, expanding the frontier of computer science to address complexities that arise in modern machine learning applications. In particular, I will show how to adapt influential ideas from statistics to create efficient algorithms that deal with inputs that are biased or unreliable. Adapting ideas from Economics, I will show how to design systems that are robust to strategic behavior of their users.
Bio
Christos Tzamos is an Assistant Professor in the Department of Computer Sciences at University of Wisconsin-Madison and a member of the Theory of Computing group. His research interests lie in the interface of Theory of Computation with Economics and Game Theory, Machine Learning, Statistics and Probability Theory. He completed his PhD in the Theory of Computation group of MIT advised by Costis Daskalakis. He studied Electrical and Computer Engineering at NTUA before his PhD, and afterwards he was a postdoctoral researcher at Microsoft Research (New England) working on Mechanism Design, Algorithms and Machine Learning. He is the recipient of a Simons Foundation award, the George M. Sprowls award, the best paper and the best student paper award in EC 2013 and of an outstanding paper award in NeurIPS 2019.
More information
Abstract
As Machine Learning is entering our lives, we are increasingly trusting many important decisions to computer systems. To create reliable and trustworthy technology, computer science must address many outstanding challenges, integrating concepts and ideas from statistics and the social sciences.
In this talk, I will present several contributions of my research, expanding the frontier of computer science to address complexities that arise in modern machine learning applications. In particular, I will show how to adapt influential ideas from statistics to create efficient algorithms that deal with inputs that are biased or unreliable. Adapting ideas from Economics, I will show how to design systems that are robust to strategic behavior of their users.
Bio
Christos Tzamos is an Assistant Professor in the Department of Computer Sciences at University of Wisconsin-Madison and a member of the Theory of Computing group. His research interests lie in the interface of Theory of Computation with Economics and Game Theory, Machine Learning, Statistics and Probability Theory. He completed his PhD in the Theory of Computation group of MIT advised by Costis Daskalakis. He studied Electrical and Computer Engineering at NTUA before his PhD, and afterwards he was a postdoctoral researcher at Microsoft Research (New England) working on Mechanism Design, Algorithms and Machine Learning. He is the recipient of a Simons Foundation award, the George M. Sprowls award, the best paper and the best student paper award in EC 2013 and of an outstanding paper award in NeurIPS 2019.
More information
Practical information
- General public
- Free
- This event is internal
Contact
- Host: Ola Svensson