Work

AG-BFGS: Foundations for Accelerated Geometry Learning

Year: 2026
Type: preprint
Abstract: We introduce an accelerated geometry-learning framework for BFGS that incorporates momentum into the learning of Hessian inverse approximations. We prove that the resulting accelerated updates satisfy explicit stability conditions and preserve positive definiteness within admissible parameter regions. Numerical experiments demonstrate consistent improvements over the corresponding non-accelerated schemes while maintaining numerical stability. These results provide the first rigorous theoretical foundation for accelerated quasi-Newton learning and bridge the gap between empirical observations and mathematical guarantees for accelerated second-order methods.
Language: English
Open Access status: green
OpenAlex ID: W7236683633
Cites:
Cited by:
Related to: 10