5 papers · 1 filter
History-Aware Adaptive High-Order Tensor Regularization
Chang He, Bo Jiang, Yuntian Jiang +2
In this paper, we develop a new adaptive regularization method for minimizing a composite function, which is the sum of a th-order () Lipschitz continuous function and…
Accelerating Trust-Region Methods: An Attempt to Balance Global and Local Efficiency
Yuntian Jiang, Chuwen Zhang, Bo Jiang +1
Balancing global efficiency and local convergence remains a central challenge in second-order methods for unconstrained convex optimization problems. Newton's method enjoys fast lo…
Inexact and Implementable Accelerated Newton Proximal Extragradient Method for Convex Optimization
Ziyu Huang, Bo Jiang, Yuntian Jiang
In this paper, we investigate the convergence behavior of the Accelerated Newton Proximal Extragradient (A-NPE) method when employing inexact Hessian information. The exact A-NPE m…
Beyond Nonconvexity: A Universal Trust-Region Method with New Analyses
Yuntian Jiang, Chang He, Chuwen Zhang +3
The trust-region (TR) method is renowned historically for its robustness in nonconvex problems and extraordinary numerical performance, but the study of its performance in convex o…
Homogeneous second-order descent framework: a fast alternative to Newton-type methods
Chang He, Yuntian Jiang, Chuwen Zhang +3
This paper proposes a homogeneous second-order descent framework (HSODF) for nonconvex and convex optimization based on the generalized homogeneous model (GHM). In comparison to th…