低预算黑箱优化的生成式精炼
Generative Refinement for Low-Budget Black-Box Optimization
浏览论文内容
中文总结 AI 辅助
提出SPARROW算法，通过解耦生成先验与奖励信号，利用固定结构化提议算子进行基于排名的引导，在极低评估预算下实现复杂几何空间和不可靠奖励信号的有效优化。
中文摘要 AI 辅助
黑箱优化是一种基础的科学与工程工具，可以在没有梯度信息的情况下优化目标函数。不幸的是，由于它通常需要大量函数评估，当每次评估代价高昂时，优化会变得具有挑战性。当评估函数存在噪声或容易失败，且高性能解局限于搜索空间的狭窄、弯曲或不连通区域时，这一问题尤为突出。现有利用生成模型导航这些子空间的方法旨在从奖励对齐的分布中采样。因此，它们需要大量评估来有效对齐采样器，在低预算设置下不实用。我们提出SPARROW算法，该算法完全解耦生成先验与奖励信号。SPARROW可以使用任何具有已知损坏过程并在未评估数据上训练的采样器，作为固定的结构化提议算子。优化通过对已评估候选档案进行基于排名的引导来进行。SPARROW能够导航复杂几何形状，处理不可靠的奖励信号，并在极低评估预算下执行有效优化。我们提供了在采样器支持上的渐近收敛保证，并在具有不可靠奖励和几何复杂景观的问题上展示了强大的实证性能。
英文摘要
Black-box optimization is a fundamental tool in science and engineering for optimizing objectives when gradient information is unavailable. It becomes especially difficult when the objective function is expensive to evaluate, limiting the evaluation budget to a few tens or hundreds of queries, and when good solutions occupy complex, low-measure regions of the search space. Generative models can supply useful structural priors in such settings, but existing generative BBO approaches bring significant evaluation cost. We identify three design principles for generative optimization under such low-budget conditions: avoid objective learning, optimize in candidate space, and make every evaluation count. Together, these principles motivate separating structural modeling from objective-driven search. We instantiate them in SPARROW, a simple sequential optimizer that maintains a persistent, ranked archive of evaluated candidates and uses a fixed, unconditional generative sampler solely as a corruption-refinement operator. SPARROW requires only access to the sampler's corruption and refinement processes, and never needs to evaluate the objective to train or guide it. Across three complementary settings, probing thin feasible geometry, disconnected high-performing regions, and failure-prone evaluations, SPARROW outperforms classical and generative baselines under strict evaluation budgets. These results demonstrate that separating structural priors from objective-driven search can be effective when evaluations are scarce and the search geometry is challenging.
发表机构
- CVLab EPFL（瑞士洛桑联邦理工学院计算机视觉实验室）
机构由 AI 辅助整理，请以论文原文为准。
