Researchers develop Fast Gauss-Newton for efficient multiclass cross-entropy optimization

Researchers have developed a Fast Gauss-Newton (FGN) method to approximate the generalized Gauss-Newton (GGN) curvature for multiclass cross-entropy. This new approach decomposes the standard GGN into a true-vs-rest term and a positive semidefinite within-competitor covariance term, dropping the latter to create an efficient under-approximation. The FGN method is exact for binary classification and can be solved efficiently using matrix-free conjugate gradient methods, showing promise for scaling up training. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Introduces a more efficient approximation for training deep learning models with many classes, potentially speeding up convergence.

RANK_REASON Academic paper detailing a new algorithmic approximation for multiclass cross-entropy. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• Fast Gauss-Newton
• Multiclass Cross-Entropy
• GGN
• softmax

• paper
• other