# Variational Depth Search in ResNets

arXiv: https://arxiv.org/abs/2002.02797 · HTML: https://mlsanity.com/paper/2002.02797/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Feb 2020.

## Built on by (most cited first, 2 of 2)

- [Depth Uncertainty Networks for Active Learning](https://mlsanity.com/paper/2112.06796/) (2021)
- [Deep Active Learning with Structured Neural Depth Search](https://mlsanity.com/paper/2306.02808/) (2023)

## Abstract (arXiv)

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. We propose a heuristic to prune our networks based on this distribution. We compare our proposed method against manual search over network depths on the MNIST, Fashion-MNIST, SVHN datasets. We find that pruned networks do not incur a loss in predictive performance, obtaining accuracies competitive with unpruned networks. Marginalising over depth allows us to obtain better-calibrated test-time uncertainty estimates than regular networks, in a single forward pass.