提出可跨模型迁移的稳定潜在变量，确保不同学习者间潜在表示可互译。
Natural Latents: Latent Variables Stable Across Ontologies
- 定义自然潜在条件，保证不同生成模型间的潜在变量可函数映射
- 证明该条件是保证可翻译性的最一般性约束
- 对近似误差鲁棒，适合实际应用中的模型对齐
假设两个贝叶斯智能体分别学习同一环境的生成模型。虽然两者在可观测变量的预测分布上已收敛，但其生成模型中包含的潜在变量可能不同。在什么条件下，一个智能体能确保自身的潜在变量是另一个智能体潜在变量的函数？本文给出了保证这种转换可能的简单条件——自然潜在条件，并证明在无额外约束下，这些条件是保证可翻译性的最一般形式。关键的是，本文定理对自然潜在条件中的近似误差具有鲁棒性，这对实际应用至关重要。
原文摘要 · Abstract (English)
Suppose two Bayesian agents each learn a generative model of the same environment. We will assume the two have converged on the predictive distribution, i.e. distribution over some observables in the environment, but may have different generative models containing different latent variables. Under what conditions can one agent guarantee that their latents are a function of the other agents latents? We give simple conditions under which such translation is guaranteed to be possible: the natural latent conditions. We also show that, absent further constraints, these are the most general conditions under which translatability is guaranteed. Crucially for practical application, our theorems are robust to approximation error in the natural latent conditions.
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。