用HiPPO提升高维贝叶斯优化的隐空间一致性，加速收敛并提高精度
HiBBO: HiPPO-based Space Consistency for High-dimensional Bayesian Optimisation
- 引入HiPPO机制建模隐空间长期依赖，增强与原始空间的分布一致性
- 在高维基准任务上收敛速度更快，最优解质量优于现有VAE-BO方法
- 适合神经架构搜索、材料科学等高维黑盒优化场景
贝叶斯优化（BO）是优化昂贵黑箱函数的强大工具，但在高维空间中因数据稀疏和代理模型可扩展性差而性能下降。基于变分自编码器（VAE）的方法通过学习低维隐空间缓解此问题，但重建损失常导致隐空间与原始空间的函数分布不匹配，影响优化效果。本文首先分析了仅用重建损失导致分布不一致的原因，提出新的HiBBO框架，通过引入基于HiPPO（一种长序列建模方法）的空间一致性约束，改进VAE隐空间构造，降低隐空间与原空间的分布偏差。在多个高维基准任务上的实验表明，HiBBO在收敛速度和解的质量上均优于现有VAE-BO方法。本工作连接了高维序列表示学习与高效贝叶斯优化，为神经架构搜索、材料科学等领域拓展了应用前景。
原文摘要 · Abstract (English)
Bayesian Optimisation (BO) is a powerful tool for optimising expensive blackbox functions but its effectiveness diminishes in highdimensional spaces due to sparse data and poor surrogate model scalability While Variational Autoencoder (VAE) based approaches address this by learning low-dimensional latent representations the reconstructionbased objective function often brings the functional distribution mismatch between the latent space and original space leading to suboptimal optimisation performance In this paper we first analyse the reason why reconstructiononly loss may lead to distribution mismatch and then propose HiBBO a novel BO framework that introduces the space consistency into the latent space construction in VAE using HiPPO - a method for longterm sequence modelling - to reduce the functional distribution mismatch between the latent space and original space Experiments on highdimensional benchmark tasks demonstrate that HiBBO outperforms existing VAEBO methods in convergence speed and solution quality Our work bridges the gap between high-dimensional sequence representation learning and efficient Bayesian Optimisation enabling broader applications in neural architecture search materials science and beyond.
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。