Tuesday, October 5, 2021
3:30 pm - 4:30 pm
154 Hurley Hall
Title: Networks: From One to Many
Networks are collections of nodes and edges that can be used to represent the interconnectedness of the world around us, from our brains and genes to our movie preferences and patterns of movement. Recent technological advances are making the collection of multiple networks, in which the network is the fundamental data object, increasingly prevalent. This motivates the desire to develop analogues to classical statistical methods for multiple networks. However, with networks being non-Euclidean, even basic tasks such as averaging are not obvious. In this talk, I will introduce networks and discuss my own research on developing the ‘Stats 101’ toolbox for multiple networks, focusing on modeling with network inputs and recovering a network from noisy unlabeled replicates. No prior background on networks is required.