Abstract: The bulk of the literature on online algorithms with ML advice focuses on a single predictor, which may or may not be correct. But, in reality, multiple ML models are often used to make future predictions for the same application, and their predictions/advice can differ from one another. In this case, how should an online algorithm choose among these different suggestions? This talk will focus on models, problems, and algorithms to address this question. The talk will include some recent results with Keerti Anand, Rong Ge, and Amit Kumar, and survey older results including an ICML '19 paper with Sreenivas Gollapudi.
Bio: Debmalya Panigrahi is a professor of computer science at Duke University. His research interests are broadly in the design and analysis of algorithms, particularly in graph algorithms and in the design of algorithms under uncertainty. His research has been recognized by an NSF CAREER Award and faculty research awards from Google and Yahoo. He obtained his PhD from MIT in 2012, where he was an MIT Presidential Fellow.
The Data Science Deep Dive is free and open to the public. If you are interested in giving a talk, please email Mohammad Hajiesmaili or Adam Lechowicz. Note that in addition to being a public lecture series, the Data Science Deep Dive is also a seminar (CompSci 692K, Algorithms with Predictions Seminar) that can be taken for credit.