Unbiased Single-Queried Gradient for Combinatorial Objective
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914330846429184 |
|---|---|
| author | Sornwanee, Thanawat |
| author_facet | Sornwanee, Thanawat |
| contents | In a probabilistic reformulation of a combinatorial problem, we often face an optimization over a hypercube, which corresponds to the Bernoulli probability parameter for each binary variable in the primal problem. The combinatorial nature suggests that an exact gradient computation requires multiple queries. We propose a stochastic gradient that is unbiased and requires only a single query of the combinatorial function. This method encompasses a well-established REINFORCE (through an importance sampling), as well as including a class of new stochastic gradients. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_05119 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Unbiased Single-Queried Gradient for Combinatorial Objective Sornwanee, Thanawat Machine Learning Optimization and Control In a probabilistic reformulation of a combinatorial problem, we often face an optimization over a hypercube, which corresponds to the Bernoulli probability parameter for each binary variable in the primal problem. The combinatorial nature suggests that an exact gradient computation requires multiple queries. We propose a stochastic gradient that is unbiased and requires only a single query of the combinatorial function. This method encompasses a well-established REINFORCE (through an importance sampling), as well as including a class of new stochastic gradients. |
| title | Unbiased Single-Queried Gradient for Combinatorial Objective |
| topic | Machine Learning Optimization and Control |
| url | https://arxiv.org/abs/2602.05119 |