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.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
CCT adds category-theoretic components to GPT-2 Small and reports a 2.92 PPL reduction on WikiText-103, localizing 84% of the gain to GT-Full simplicial message passing via ablation.
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.