Date:
Wednesday, September 14, 2022 – 12:15 to 13:00
Location:
Marcus Nano building, Rooms 1116-1118
Summary Sentence:
This talk will describe two research vignettes in full-information and bandit learning.
Contact:
Lia Namirr
Machine Learning Center at Georgia Tech
Abstract: Classical online learning algorithms make a static assumption on the nature of the data generating process (either stochastic or adversarial) and the nature of the offline benchmark to measure performance. Neither of these assumptions are well-justified in practice. While assuming a probability model on the data could lead to suboptimal performance in practice, worst-case adversarially robust algorithms may be unnecessarily pessimistic.
Event Categories:
Invited Audience: