Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.11639 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915872526827520 |
|---|---|
| author | Li, Ming |
| author_facet | Li, Ming |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_11639 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Global Optimization By Gradient From Hierarchical Score-Matching Spaces Li, Ming Machine Learning 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. |
| title | Global Optimization By Gradient From Hierarchical Score-Matching Spaces |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2601.11639 |