用扩散模型生成多目标优化解，兼顾效率与多样性。
SPREAD: Sampling-based Pareto front Refinement via Efficient Adaptive Diffusion
- 基于扩散模型学习决策空间分布，逐步优化候选解
- 自适应梯度更新加速收敛，高斯RBF排斥保持解多样性
- 在多个基准上优于或媲美现有方法，适合大规模优化
高效求解多目标优化中的帕累托集仍是关键挑战，尤其针对大规模和高成本问题。为此，我们提出SPREAD，一种基于去噪扩散概率模型（DDPM）的生成框架。SPREAD首先在决策空间采样点上学习条件扩散过程，然后在每一步反向扩散中，通过结合自适应多梯度下降更新实现快速收敛，并引入基于高斯RBF的排斥项以增强解的多样性。在多个多目标优化基准测试中，包括离线和基于贝叶斯代理模型的设置，实验结果表明SPREAD在效率、可扩展性和帕累托前沿覆盖率方面均达到或超过领先基线。代码已开源：https://github.com/safe-autonomous-systems/moo-spread。
原文摘要 · Abstract (English)
Developing efficient multi-objective optimization methods to compute the Pareto set of optimal compromises between conflicting objectives remains a key challenge, especially for large-scale and expensive problems. To bridge this gap, we introduce SPREAD, a generative framework based on Denoising Diffusion Probabilistic Models (DDPMs). SPREAD first learns a conditional diffusion process over points sampled from the decision space and then, at each reverse diffusion step, refines candidates via a sampling scheme that uses an adaptive multiple gradient descent-inspired update for fast convergence alongside a Gaussian RBF-based repulsion term for diversity. Empirical results on multi-objective optimization benchmarks, including offline and Bayesian surrogate-based settings, show that SPREAD matches or exceeds leading baselines in efficiency, scalability, and Pareto front coverage. Code is available at https://github.com/safe-autonomous-systems/moo-spread .
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。