Global Optimization By Gradient From Hierarchical Score-Matching Spaces
Not on the map. Why?
Abstract (arXiv)
Gradient-based methods are widely used to solve various optimization problems, however, they are either constrained by local optima dilemmas, simple convex constraints, and continuous differentiability requirements, or limited to low-dimensional simple problems. This work solve these limitations and restrictions by unifying all optimization problems with various complex constraints as a general hierarchical optimization objective without constraints, which is optimized by gradient obtained through score matching. The proposed method is verified through simple-constructed and complex-practical experiments. Even more importantly, it reveals the profound connection between global optimization and diffusion based generative modeling.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). First posted on arXiv 14 Jan 2026.
Builds on
0 of 0 references.
No references here yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Algorithm- and Data-Dependent Generalization Bounds for Diffusion Models
- 2026Non-asymptotic Convergence of Stochastic Gradient Descent in Score-based Generative Models
- 2025Convergence Dynamics of Over-Parameterized Score Matching for a Single Gaussian
- 2024Diffusion Model for Data-Driven Black-Box Optimization
- 2024Guided Trajectory Generation with Diffusion Models for Offline Model-based Optimization
- 2025Score as Action: Fine-Tuning Diffusion Generative Models by Continuous-time Reinforcement Learning
- 2023Preconditioned Score-based Generative Models
- 2024Analyzing Neural Network-Based Generative Diffusion Models through Convex Optimization