Variational Depth Search in ResNets

6 Feb 2020Javier AntoránJames Urquhart AllinghamJosé Miguel Hernández-Lobato

One-shot neural architecture search allows joint learning of weights and network architecture, reducing computational cost. We limit our search space to the depth of residual networks and formulate an analytically tractable variational objective that allows for obtaining an unbiased approximate posterior over depths in one-shot... (read more)

PDF Abstract

Evaluation Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.