# To Ensemble or Not Ensemble: When does End-To-End Training Fail?

arXiv: https://arxiv.org/abs/1902.04422 · HTML: https://mlsanity.com/paper/1902.04422/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Feb 2019.

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

- [Deep Multi-View Learning for Tire Recommendation](https://mlsanity.com/paper/2203.12451/) (2022)
- [Virtual neural networks: hundreds of souls in a body](https://mlsanity.com/paper/2609.24782/) (2026)

## Abstract (arXiv)

End-to-End training (E2E) is becoming more and more popular to train complex Deep Network architectures. An interesting question is whether this trend will continue-are there any clear failure cases for E2E training? We study this question in depth, for the specific case of E2E training an ensemble of networks. Our strategy is to blend the gradient smoothly in between two extremes: from independent training of the networks, up to to full E2E training. We find clear failure cases, where over-parameterized models cannot be trained E2E. A surprising result is that the optimum can sometimes lie in between the two, neither an ensemble or an E2E system. The work also uncovers links to Dropout, and raises questions around the nature of ensemble diversity and multi-branch networks.