pith. sign in

Title resolution pending

For networks with element-wise activation functions (ReLU, sigmoid), where tensorsTu, v andT u, v,w are diagonal or sparse withO(d)cost, the total time reduces toO(nsd2 +nsdP+P 2)

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

Title metadata for this work has not finished resolving. The hub is built from the citation graph; the title resolver retries DOI and OpenAlex on its next pass.

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Inter-Layer Hessian Analysis of Neural Networks with DAG Architectures

cs.LG · 2026-04-13 · unverdicted · novelty 6.0

The paper derives a DAG-indexed block decomposition of the neural network Hessian into Gauss-Newton and tensor components and introduces stochastic O(P) metrics for inter-layer curvature interactions such as resonance and geometric coupling.

citing papers explorer

Showing 1 of 1 citing paper.

  • Inter-Layer Hessian Analysis of Neural Networks with DAG Architectures cs.LG · 2026-04-13 · unverdicted · none · ref 9

    The paper derives a DAG-indexed block decomposition of the neural network Hessian into Gauss-Newton and tensor components and introduces stochastic O(P) metrics for inter-layer curvature interactions such as resonance and geometric coupling.