تقرير
Safe Screening for Unbalanced Optimal Transport
| العنوان: | Safe Screening for Unbalanced Optimal Transport |
|---|---|
| المؤلفون: | Su, Xun, Fang, Zhongxi, Kasai, Hiroyuki |
| سنة النشر: | 2023 |
| المجموعة: | Computer Science Mathematics |
| مصطلحات موضوعية: | Mathematics - Optimization and Control, Computer Science - Machine Learning |
| الوصف: | This paper introduces a framework that utilizes the Safe Screening technique to accelerate the optimization process of the Unbalanced Optimal Transport (UOT) problem by proactively identifying and eliminating zero elements in the sparse solutions. We demonstrate the feasibility of applying Safe Screening to the UOT problem with $\ell_2$-penalty and KL-penalty by conducting an analysis of the solution's bounds and considering the local strong convexity of the dual problem. Considering the specific structural characteristics of the UOT in comparison to general Lasso problems on the index matrix, we specifically propose a novel approximate projection, an elliptical safe region construction, and a two-hyperplane relaxation method. These enhancements significantly improve the screening efficiency for the UOT's without altering the algorithm's complexity. |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2307.00247 |
| رقم الأكسشن: | edsarx.2307.00247 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |