Events

Shift happens: how can we best prepare?

Speaker: Cian Eastwood

Location: 60 Fifth Avenue, Room 527

Date: Friday, December 9, 2022

The conditions under which a model is developed usually differ from those in which it is deployed. Thus, to be useful in practice, machine learning systems must be developed with such condition/distribution shifts in mind. In this talk, I will discuss several ways in which we have sought to prepare models for distribution shift under the umbrella terms of domain adaptation, domain generalization and causal/disentangled representation learning. I'll end by discussing open questions and possible future avenues.