用神经网络模拟退火过程，高效求解难以优化的组合问题。
A Generative Neural Annealer for Black-Box Combinatorial Optimization
- 构建可端到端训练的生成模型，模拟退火中的能量分布。
- 在有限查询下表现优异，比现有方法更省样本。
- 适合高成本查询或复杂变量交互的黑箱优化场景。
我们提出一种生成式端到端求解器，用于黑箱组合优化，强调在NP问题上的样本效率与解的质量。受退火算法启发，将黑箱目标函数视为能量函数，训练神经网络建模相应的玻尔兹曼分布。通过温度条件控制，网络捕捉从高温下的近似均匀分布到低温下集中于全局最优的分布连续体，从而学习能量景观结构并促进全局优化。当查询代价高昂时，温度相关的分布自然实现数据增强，提升样本效率；当查询成本低但问题仍困难时，模型学习隐式变量交互，有效‘打开’黑箱。我们在受限和无限查询预算下验证该方法，在多个挑战性组合任务中表现优于现有先进黑箱优化器。
原文摘要 · Abstract (English)
We propose a generative, end-to-end solver for black-box combinatorial optimization that emphasizes both sample efficiency and solution quality on NP problems. Drawing inspiration from annealing-based algorithms, we treat the black-box objective as an energy function and train a neural network to model the associated Boltzmann distribution. By conditioning on temperature, the network captures a continuum of distributions--from near-uniform at high temperatures to sharply peaked around global optima at low temperatures--thereby learning the structure of the energy landscape and facilitating global optimization. When queries are expensive, the temperature-dependent distributions naturally enable data augmentation and improve sample efficiency. When queries are cheap but the problem remains hard, the model learns implicit variable interactions, effectively "opening" the black box. We validate our approach on challenging combinatorial tasks under both limited and unlimited query budgets, showing competitive performance against state-of-the-art black-box optimizers.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。