| Title | : | Robustness in Sequential Learning: Demystifying Heavy Tails |
| Speaker | : | Dr. Shubhada Agrawal (Herbert A. Johnson Postdoctoral Fellow, Georgia Tech) |
| Details | : | Tue, 16 Jan, 2024 11:00 AM @ SSB-233 |
| Abstract: | : | Numerous real-world machine learning applications involve making decisions sequentially through dynamic interactions with the environment. Tech giants like Google and Meta use sequential learning algorithms to generate billions in revenue. However, their adoption in safety-critical domains like healthcare, defence, and autonomous vehicles is low due to a limited understanding of their behaviour in diverse practical environments. In this talk, we will look at designing robust algorithms safe for real-world applications. For concreteness, we will consider the classical regret minimization problem in the multi-armed bandit (MAB) setting with minimal assumptions about the arm distributions. We will discuss an optimal algorithm for this problem and the ideas involved in its design and analysis. I will also briefly present an overview of my other works in this space and conclude with future research directions I am excited about. |
