arXiv Open Access 2019

Contrastive Learning for Lifted Networks

Christopher Zach Virginia Estellers
Lihat Sumber

Abstrak

In this work we address supervised learning of neural networks via lifted network formulations. Lifted networks are interesting because they allow training on massively parallel hardware and assign energy models to discriminatively trained neural networks. We demonstrate that the training methods for lifted networks proposed in the literature have significant limitations and show how to use a contrastive loss to address those limitations. We demonstrate that this contrastive training approximates back-propagation in theory and in practice and that it is superior to the training objective regularly used for lifted networks.

Topik & Kata Kunci

Penulis (2)

C

Christopher Zach

V

Virginia Estellers

Format Sitasi

Zach, C., Estellers, V. (2019). Contrastive Learning for Lifted Networks. https://arxiv.org/abs/1905.02507

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2019
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓