Research
Quasi-Quadratic Gradient: A New Direction for Accelerating the BFGS Method in Quasi-Newton Optimization
arXiv:2604.23922v1 Announce Type: cross Abstract: In this paper, we introduce the Quasi-Quadratic Gradient (QQG), a novel search direction designed to accelerate the BFGS method within the quasi-Newto
arXiv:2604.23922v1 Announce Type: cross Abstract: In this paper, we introduce the Quasi-Quadratic Gradient (QQG), a novel search direction designed to accelerate the BFGS method within the quasi-Newton framework. By defining the QQG as the product of the inverse Hessian approximation and the current gradient, we explicitly leverage local second-order curvature to rectify the search path. Theoretical analysis and empirical results demonstrate that our approach significantly outperforms vanilla BFGS in convergence speed while maintaining computational efficiency.
Related
- Auto-Unrolled Proximal Gradient Descent: An AutoML Approach to Interpretable Waveform Optimization
- AXIL: Exact Instance Attribution for Gradient Boosting
- GRACE: A Dynamic Coreset Selection Framework for Large Language Model Optimization
- A general optimization solver based on OP-to-MaxSAT reduction
Source: arXiv cs.AI | 2026-04-28