Broximal Alignment for Global Non-Convex Optimization

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Gruntkowska, Kaja, Li, Hanmin, Qian, Xun, Richtárik, Peter
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915937997815808
author Gruntkowska, Kaja
Li, Hanmin
Qian, Xun
Richtárik, Peter
author_facet Gruntkowska, Kaja
Li, Hanmin
Qian, Xun
Richtárik, Peter
contents Most non-convex optimization theory is built around gradient dynamics, leaving global convergence largely unexplored. The dominant paradigm focuses on stationarity, certifying only that the gradient norm vanishes, which is often a weak proxy for actual optimization success. In practice, gradient norms can stagnate or even increase during training, and stationary points may be far from global solutions. In this work, we propose a new framework for global non-convex optimization that avoids gradient-based reasoning altogether. We revisit the Ball Proximal Point Method (BPM), a trust-region-style algorithm introduced by Gruntkowska et al. (2025), and propose a novel structural condition - Broximal Alignment - under which BPM provably converges to a global minimizer. Our condition requires no convexity, smoothness, or Lipschitz assumptions, and it permits multiple and disconnected global minima as well as non-optimal local minima. We show that this class generalizes standard non-convex frameworks such as quasiconvexity, star convexity, quasar convexity, and the aiming condition. Our results provide a new conceptual foundation for global non-convex optimization beyond stationarity.
format Preprint
id arxiv_https___arxiv_org_abs_2604_13483
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Broximal Alignment for Global Non-Convex Optimization
Gruntkowska, Kaja
Li, Hanmin
Qian, Xun
Richtárik, Peter
Optimization and Control
Most non-convex optimization theory is built around gradient dynamics, leaving global convergence largely unexplored. The dominant paradigm focuses on stationarity, certifying only that the gradient norm vanishes, which is often a weak proxy for actual optimization success. In practice, gradient norms can stagnate or even increase during training, and stationary points may be far from global solutions. In this work, we propose a new framework for global non-convex optimization that avoids gradient-based reasoning altogether. We revisit the Ball Proximal Point Method (BPM), a trust-region-style algorithm introduced by Gruntkowska et al. (2025), and propose a novel structural condition - Broximal Alignment - under which BPM provably converges to a global minimizer. Our condition requires no convexity, smoothness, or Lipschitz assumptions, and it permits multiple and disconnected global minima as well as non-optimal local minima. We show that this class generalizes standard non-convex frameworks such as quasiconvexity, star convexity, quasar convexity, and the aiming condition. Our results provide a new conceptual foundation for global non-convex optimization beyond stationarity.
title Broximal Alignment for Global Non-Convex Optimization
topic Optimization and Control
url https://arxiv.org/abs/2604.13483