pith. sign in

Diagonalizing the softmax: Hadamard initialization for tractable cross-entropy dynamics.arXiv preprint arXiv:2512.04006

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

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

The Neural Tangent Kernel for Classification

cs.LG · 2026-05-17 · unverdicted · novelty 6.0 · 2 refs

Wide neural networks with cross-entropy loss remain in the lazy training regime under parameter-space regularization or non-degenerate targets, allowing explicit NTK-based solution characterization and uncertainty analysis.

citing papers explorer

Showing 1 of 1 citing paper.

  • The Neural Tangent Kernel for Classification cs.LG · 2026-05-17 · unverdicted · none · ref 2 · 2 links

    Wide neural networks with cross-entropy loss remain in the lazy training regime under parameter-space regularization or non-degenerate targets, allowing explicit NTK-based solution characterization and uncertainty analysis.