贝叶斯优化结合摊销逆映射:缩小搜索空间的新方法
Bayesian optimization on amortized search space
搞黑盒优化的朋友可以看看这篇:先离线训一个摊销网络把搜索空间压到低维,再用高斯过程在线优化。比直接在原始参数上搜GP更省评估次数, regret 理论也给了保证,做药物剂量或仿真优化的团队能直接借鉴。
一篇 arXiv 论文提出在贝叶斯优化中利用模拟器的摊销逆映射来限制搜索空间。方法用高斯过程核保持原问题几何结构,从而高效利用优化问题的低内在维度。
技术上,先针对机械模拟器(如 PK/PD 药代动力学/药效学模型)离线训练一个摊销网络,把患者参数映射到预测最优方案,再让在线贝叶斯优化在这个学到的低维表示上搜索,而非在原始剂量空间上搜索。论文刻画了近似偏差和信息增益,并在几何与高斯过程假设下推导出依赖内在维度的遗憾率。
实验以帕金森病药物剂量个性化为应用场景,数值模拟显示该方法在性能上优于基线,且在模拟器存在误设时依然稳健。
Bayesian optimization on amortized search space
In real-world black-box optimization problems, a mechanistic simulator is often available that approximately predicts the behavior of the system as a function of the parameters being optimized. Here, we show how an amortized inverse map of such a simulator can be used in Bayesian optimization to restrict the search space while using a Gaussian process kernel that is aware of the original problem geometry. This allows for efficiently leveraging the low intrinsic dimensionality of the optimization problem. We characterize its approximation bias and information gain, and derive an intrinsic-dimension-dependent regret rate under additional geometric and Gaussian Process assumptions. We illustrate the method with an application to drug dosing personalization in Parkinson's disease. We use, as a simulator, a pharmacokinetic/pharmacodynamic (PK/PD) model of a drug, a mechanistic model calibrated on population data with quantified parameter uncertainty. A dosing neural network is trained offline against the model, amortizing the map from patient PK/PD parameters to the regimen predicted to be optimal, and online Bayesian optimization then searches over this learned, low-dimensional representation rather than over raw dosages. Numerical simulations demonstrate the improved performance of our method in this application, as well as under simulator misspecification.
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Bayesian optimization, Gaussian Process, PK/PD.
Source attribution: curated from arXiv cs.LG (@Tristan Fauvel, Federico Pavone, Titouan Guillou, Pau Redon Muñoz, Chloé Geoffroy).