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.
Original language | English (US) |
---|---|
Pages (from-to) | 8789-8798 |
Number of pages | 10 |
Journal | Advances in Neural Information Processing Systems |
Volume | 2018-December |
State | Published - 2018 |
Event | 32nd Conference on Neural Information Processing Systems, NeurIPS 2018 - Montreal, Canada Duration: Dec 2 2018 → Dec 8 2018 |
ASJC Scopus subject areas
- Computer Networks and Communications
- Information Systems
- Signal Processing