Nexus matches standard pretraining loss while improving downstream and OOD performance by maximizing gradient similarity so task-specific minima stay close.
arXiv preprint arXiv:2211.05729 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 3roles
background 2polarities
background 2representative citing papers
SAGE, an optimizer combining spectral polar-factor perturbation with gradient-agreement-scaled noise, reports 78.9% average on DomainBed.
A mechanics of the learning process is emerging in deep learning theory, characterized by dynamics, coarse statistics, and falsifiable predictions across idealized settings, limits, laws, hyperparameters, and universal behaviors.
citing papers explorer
-
Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima
Nexus matches standard pretraining loss while improving downstream and OOD performance by maximizing gradient similarity so task-specific minima stay close.
-
Flatness and Gradient Alignment Are Both Necessary: Spectral-Aware Gradient-Aligned Exploration for Multi-Distribution Learning
SAGE, an optimizer combining spectral polar-factor perturbation with gradient-agreement-scaled noise, reports 78.9% average on DomainBed.
-
There Will Be a Scientific Theory of Deep Learning
A mechanics of the learning process is emerging in deep learning theory, characterized by dynamics, coarse statistics, and falsifiable predictions across idealized settings, limits, laws, hyperparameters, and universal behaviors.