让实验设计策略在测试时动态优化，提升灵活性与鲁棒性。
Step-DAD: Semi-Amortized Policy-Based Bayesian Experimental Design
- 先训练再更新：前期训练策略，实验中随数据持续优化。
- 实测优于当前最优方法，决策更准、抗干扰更强。
- 适合需要动态调整的实验场景，如临床试验、机器人探索。
我们提出一种半摊销、基于策略的贝叶斯实验设计方法 Step-DAD。与现有全摊销策略方法类似，Step-DAD 在实验前预先训练设计策略。但不同于固定不变的策略，Step-DAD 在实验过程中根据累积数据周期性地更新策略，使其适应具体实验实例。这种测试时的自适应机制提升了设计策略的灵活性与鲁棒性。实验表明，Step-DAD 在决策性能和稳健性方面均持续优于当前最先进的贝叶斯实验设计方法。
原文摘要 · Abstract (English)
We develop a semi-amortized, policy-based, approach to Bayesian experimental design (BED) called Stepwise Deep Adaptive Design (Step-DAD). Like existing, fully amortized, policy-based BED approaches, Step-DAD trains a design policy upfront before the experiment. However, rather than keeping this policy fixed, Step-DAD periodically updates it as data is gathered, refining it to the particular experimental instance. This test-time adaptation improves both the flexibility and the robustness of the design strategy compared with existing approaches. Empirically, Step-DAD consistently demonstrates superior decision-making and robustness compared with current state-of-the-art BED methods.
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。