PC-ALM uses dual ascent on an augmented Lagrangian to achieve exact backpropagation gradients via layer-local updates in linear networks and matching performance in nonlinear networks up to depth 128.
Contrastive Learning for Lifted Networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
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.
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Augmented Lagrangian Predictive Coding
PC-ALM uses dual ascent on an augmented Lagrangian to achieve exact backpropagation gradients via layer-local updates in linear networks and matching performance in nonlinear networks up to depth 128.