NeurIPS 2019
Sun Dec 8th through Sat the 14th, 2019 at Vancouver Convention Center
Paper ID:6001
Title:Meta Architecture Search

This paper shows how to apply transfer learning from related tasks to NAS. It proposes a variational Bayesian formulation, which is related to earlier work, but the transfer learning approach is novel, and is clearly useful, given that NAS people can assemble a sufficient number of tasks over time. As detailed in the reviews, the experimental validation could be improved.