Finding Probably Approximate Optimal Solutions by Training to Estimate the Optimal Values of Subproblems
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918184655781888 |
|---|---|
| author | Megiddo, Nimrod Wasserkrug, Segev Davidovich, Orit Shtern, Shimrit |
| author_facet | Megiddo, Nimrod Wasserkrug, Segev Davidovich, Orit Shtern, Shimrit |
| contents | The paper is about developing a solver for maximizing a real-valued function of binary variables. The solver relies on an algorithm that estimates the optimal objective-function value of instances from the underlying distribution of objectives and their respective sub-instances. The training of the estimator is based on an inequality that facilitates the use of the expected total deviation from optimality conditions as a loss function rather than the objective-function itself. Thus, it does not calculate values of policies, nor does it rely on solved instances. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_02048 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Finding Probably Approximate Optimal Solutions by Training to Estimate the Optimal Values of Subproblems Megiddo, Nimrod Wasserkrug, Segev Davidovich, Orit Shtern, Shimrit Machine Learning The paper is about developing a solver for maximizing a real-valued function of binary variables. The solver relies on an algorithm that estimates the optimal objective-function value of instances from the underlying distribution of objectives and their respective sub-instances. The training of the estimator is based on an inequality that facilitates the use of the expected total deviation from optimality conditions as a loss function rather than the objective-function itself. Thus, it does not calculate values of policies, nor does it rely on solved instances. |
| title | Finding Probably Approximate Optimal Solutions by Training to Estimate the Optimal Values of Subproblems |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2511.02048 |