pith. machine review for the scientific record. sign in

Training neural networks with stochastic Hessian-free optimization

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

Fast Gauss-Newton for Multiclass Cross-Entropy

cs.LG · 2026-05-07 · unverdicted · novelty 7.0

FGN is a positive semidefinite under-approximation of the multiclass GGN obtained by exact decomposition into true-vs-rest and within-competitor terms, exact for binary classification and implemented via matrix-free conjugate gradient on a whitened row-space system.

citing papers explorer

Showing 1 of 1 citing paper.

  • Fast Gauss-Newton for Multiclass Cross-Entropy cs.LG · 2026-05-07 · unverdicted · none · ref 17

    FGN is a positive semidefinite under-approximation of the multiclass GGN obtained by exact decomposition into true-vs-rest and within-competitor terms, exact for binary classification and implemented via matrix-free conjugate gradient on a whitened row-space system.