DeLTA seminar by Amartya Sanyal
Amartya Sanyal, ETH
Trustworthy Machine Learning under statistical limitations
Machine Learning (ML) algorithms are known to suffer from various issues when it comes to their trustworthiness including properties like adversarial robustness, privacy, and fairness. While there has been significant progress in developing new trustworthy algorithms, the role of inadequate data is often ignored. Widely available data in the real world are often noisy, limited, and long-tailed and play a key role in hindering these aspects of trustworthiness. In this talk, we will look at characterising some of the fundamental limitations on trustworthiness due to inadequate data. In the first half of the talk, we will consider the role of noisy data on adversarial robustness. In the second half, we will look at the role of long-tailed data on private learning and fairness. In both of these topics, we will look at theoretical results as well as experimental evidence to back them up.
You can subscribe to the DeLTA Seminar mailing list by sending an empty email to email@example.com.
DeLTA Lab page
DeLTA is a research group affiliated with the Department of Computer Science at the University of Copenhagen studying diverse aspects of Machine Learning Theory and its applications, including, but not limited to Reinforcement Learning, Online Learning and Bandits, PAC-Bayesian analysis