Skip to yearly menu bar Skip to main content


Poster

Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs

Timur Garipov · Pavel Izmailov · Dmitrii Podoprikhin · Dmitry Vetrov · Andrew Wilson

Room 517 AB #162

Keywords: [ Supervised Deep Networks ] [ Computer Vision ] [ Boosting and Ensemble Methods ] [ Visualization or Exposition Techniques for Deep Networks ]


Abstract:

The loss functions of deep neural networks are complex and their geometric properties are not well understood. We show that the optima of these complex loss functions are in fact connected by simple curves, over which training and test accuracy are nearly constant. We introduce a training procedure to discover these high-accuracy pathways between modes. Inspired by this new geometric insight, we also propose a new ensembling method entitled Fast Geometric Ensembling (FGE). Using FGE we can train high-performing ensembles in the time required to train a single model. We achieve improved performance compared to the recent state-of-the-art Snapshot Ensembles, on CIFAR-10, CIFAR-100, and ImageNet.

Live content is unavailable. Log in and register to view live content