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.
Optimizing neural networks with kronecker-factored approx- imate curvature
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
fields
cs.LG 5years
2026 5roles
background 3polarities
background 3representative citing papers
Gauss-Newton descent whitens errors by projecting Newton directions or gradients onto the tangent space, replacing JJ^T with the identity and removing parameterization distortions that affect Newton descent.
AdaPreLoRA pairs the Adafactor diagonal Kronecker preconditioner on the full weight matrix with a closed-form factor-space solve that selects the update minimizing an H_t-weighted imbalance, yielding competitive results on GPT-2, Mistral-7B, Qwen2-7B and diffusion personalization tasks.
MuonEq introduces pre-orthogonalization equilibration schemes that improve Muon optimizer performance during large language model pretraining.