The training problem for deep linear neural networks under squared loss admits an exact convex reformulation in a lifted space over a generalized completely positive cone, with dimension independent of depth.
Convex formulations for training two-layer ReLU neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Exact Convex Reformulations of Linear Neural Networks via Completely Positive Lifting
The training problem for deep linear neural networks under squared loss admits an exact convex reformulation in a lifted space over a generalized completely positive cone, with dimension independent of depth.