提出可组合的变分推断框架，统一建模与优化流程。
AutoBayes: A Compositional Framework for Generalized Variational Inference
- 将模型构建、反演、损失函数连接等操作视为可组合模块。
- 发现精确贝叶斯推断与变分目标均满足类似反向传播的链式法则。
- 适用于需灵活设计推断流程的研究者，尤其适合复杂模型开发。
我们提出一种新的可组合变分推断框架，明确模型各部分的构成、交互方式及其组合规律。我们指出，精确贝叶斯推断以及典型的变分推断损失函数（如变分自由能及其推广形式）均满足类似于反向自动微分的链式法则，并主张利用这一特性来构建和优化模型。为此，我们开发了一系列可组合工具：用于构建模型；构造其逆模型；附加局部损失函数；暴露参数。最后，我们说明所得参数化统计博弈也可进行局部优化。通过一系列经典例子展示该框架，揭示了新的可扩展方向。
原文摘要 · Abstract (English)
We introduce a new compositional framework for generalized variational inference, clarifying the different parts of a model, how they interact, and how they compose. We explain that both exact Bayesian inference and the loss functions typical of variational inference (such as variational free energy and its generalizations) satisfy chain rules akin to that of reverse-mode automatic differentiation, and we advocate for exploiting this to build and optimize models accordingly. To this end, we construct a series of compositional tools: for building models; for constructing their inversions; for attaching local loss functions; and for exposing parameters. Finally, we explain how the resulting parameterized statistical games may be optimized locally, too. We illustrate our framework with a number of classic examples, pointing to new areas of extensibility that are revealed.
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。