Linesearch-Free Nonlinearly Preconditioned GD with Semiautomatic Geometry Design
Abstract
Nonlinear preconditioning makes it possible to adapt gradient updates to the growth of the objective's curvature, but combining its design with suitable stepsize selection is challenging. We propose adaptive dual preconditioned gradient descent (adaptive DPGD), which combines curvature-based preconditioner design with a linesearch-free stepsize rule based on local information. For convex objectives, we establish linear convergence under local strong convexity of the objective. By adapting the stepsize rule, we extend the method to weakly convex objectives and establish asymptotic stationarity without global Lipschitz smoothness. Moreover, our local assumptions give greater freedom in preconditioner design. We exploit this freedom to develop a semiautomatic recipe guided by the objective's curvature, yielding a family of preconditioners that includes those underlying normalized and hyperbolic gradient descent. Experiments on convex and weakly convex problems with real data demonstrate the effectiveness of the preconditioner design and adaptive stepsize selection.
Related
- Global Solution Branches of Forced Nonlinearly Elastic Single-Director Surfaces
- Asymptotic stability and sharp decay near homogeneous solutions of a nonlinearly damped Schrödinger equation on the torus
- A Stochastic LineseArch Method (SLAM) for Minimizing Expectation Residuals: Weakening Boundedness of Gradient
- Design of convergent profiles for shock tubes in spherical geometry
- Primal-dual forward-reflected splitting with linesearch for distributed min-max problems under local Lipschitz smoothness
BibTeX
@misc{iwade2026linesearchfree,
title = {{Linesearch-Free Nonlinearly Preconditioned GD with Semiautomatic Geometry Design}},
author = {Daiki Iwade and Shota Takahashi and Akiko Takeda},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.34288},
eprint = {2609.34288},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.34288},
}
RIS
TY - UNPB
TI - Linesearch-Free Nonlinearly Preconditioned GD with Semiautomatic Geometry Design
AU - Daiki Iwade
AU - Shota Takahashi
AU - Akiko Takeda
PY - 2026
DA - 2026/09/28
PB - arXiv
DO - 10.48550/arxiv.2609.34288
UR - https://arxiv.org/abs/2609.34288
AB - Nonlinear preconditioning makes it possible to adapt gradient updates to the growth of the objective's curvature, but combining its design with suitable stepsize selection is challenging. We propose adaptive dual preconditioned gradient descent (adaptive DPGD), which combines curvature-based preconditioner design with a linesearch-free stepsize rule based on local information. For convex objectives, we establish linear convergence under local strong convexity of the objective. By adapting the stepsize rule, we extend the method to weakly convex objectives and establish asymptotic stationarity without global Lipschitz smoothness. Moreover, our local assumptions give greater freedom in preconditioner design. We exploit this freedom to develop a semiautomatic recipe guided by the objective's curvature, yielding a family of preconditioners that includes those underlying normalized and hyperbolic gradient descent. Experiments on convex and weakly convex problems with real data demonstrate the effectiveness of the preconditioner design and adaptive stepsize selection.
ER -