Snapshot Ensembles: Train 1, get M for free

Gao Huang,Yixuan Li,Geoff Pleiss,Zhuang Liu,J. Hopcroft,Kilian Q. Weinberger

Published 2017 in International Conference on Learning Representations

ABSTRACT

Ensembles of neural networks are known to be much more robust and accurate than individual networks. However, training multiple deep networks for model averaging is computationally expensive. In this paper, we propose a method to obtain the seemingly contradictory goal of ensembling multiple neural networks at no additional training cost. We achieve this goal by training a single neural network, converging to several local minima along its optimization path and saving the model parameters. To obtain repeated rapid convergence, we leverage recent work on cyclic learning rate schedules. The resulting technique, which we refer to as Snapshot Ensembling, is simple, yet surprisingly effective. We show in a series of experiments that our approach is compatible with diverse network architectures and learning tasks. It consistently yields lower error rates than state-of-the-art single models at no additional training cost, and compares favorably with traditional network ensembles. On CIFAR-10 and CIFAR-100 our DenseNet Snapshot Ensembles obtain error rates of 3.4% and 17.4% respectively.

PUBLICATION RECORD

  • Publication year

    2017

  • Venue

    International Conference on Learning Representations

  • Publication date

    2017-04-01

  • Fields of study

    Computer Science

  • Identifiers
  • External record

    Open on Semantic Scholar

  • Source metadata

    Semantic Scholar

CITATION MAP

EXTRACTION MAP

CLAIMS

  • No claims are published for this paper.

CONCEPTS

  • No concepts are published for this paper.

REFERENCES

Showing 1-44 of 44 references · Page 1 of 1

CITED BY

Showing 1-100 of 1051 citing papers · Page 1 of 11