arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.26147cs.LG
收藏

神经贝叶斯序列路由

Neural Bayesian Sequential Routing

Yongchao Huang

AI总结:

提出神经贝叶斯序列路由(NBSR)框架,将神经推理建模为有向无环图上的主动证据累积,通过狄利克雷-分类共轭框架实现不确定性量化、早期退出和资源理性推理。

摘要:

人类决策是序列化的且具有不确定性意识,然而标准神经网络通常依赖静态、密集的前向计算,对证据获取、不确定性演化或何时停止计算的可视性有限。我们引入了 extbf{神经贝叶斯序列路由(NBSR)},这是一个将神经推理建模为层次化有向无环图(DAG)上的主动证据累积的框架。在狄利克雷-分类共轭框架内,神经专家查询一个持久的全局知识预言机以提取正证据向量,这些向量作为伪计数,通过精确共轭加法更新狄利克雷信念状态。结合Gumbel-Softmax直通估计器,该更新实现了硬性、路径依赖的路由,同时保留用于端到端训练的代理梯度。由此产生的狄利克雷精度和熵为不确定性量化、基于熵的早期退出、分布外(OOD)弃权以及成本感知的证据获取提供了机制。我们证明,在严格正证据提取下,总狄利克雷精度沿任何有效轨迹单调增加,边际预测方差有界,形式化了序列“假设锐化”;在理想容量和优化假设下,终端狄利克雷期望恢复贝叶斯最优条件分布。在视觉分类、结构化医学诊断、语言建模、部分可观测控制以及成本感知贝叶斯实验设计上的实证评估表明,NBSR在提供透明的路由轨迹、路径依赖的证据归因、不确定性感知的决策控制以及资源理性推理的同时,实现了具有竞争力的预测性能。总体而言,NBSR为可解释、模块化和资源理性的智能体AI提供了一个数学上坚实的框架。

英文摘要:

Human decision-making is sequential and uncertainty-aware, yet standard neural networks often rely on static, dense forward computation with limited visibility into evidence acquisition, uncertainty evolution, or when computation should stop. We introduce \textbf{Neural Bayesian Sequential Routing (NBSR)}, a framework that models neural inference as active evidence accumulation over a hierarchical Directed Acyclic Graph (DAG). Within a Dirichlet--Categorical conjugate framework, neural experts query a persistent global knowledge oracle to extract positive evidence vectors, which act as pseudo-counts and update a Dirichlet belief state by exact conjugate addition. Coupled with a Gumbel-Softmax Straight-Through estimator, this update enables hard, path-dependent routing while preserving surrogate gradients for end-to-end training. The resulting Dirichlet precision and entropy provide mechanisms for uncertainty quantification, entropy-based early exiting, OOD abstention, and cost-aware evidence acquisition. We prove that, under strictly positive evidence extraction, total Dirichlet precision increases monotonically along any valid trajectory and marginal predictive variance is bounded, formalizing sequential ``hypothesis sharpening''; under idealized capacity and optimization assumptions, the terminal Dirichlet expectation recovers the Bayes-optimal conditional distribution. Empirical evaluations across visual categorization, structured medical diagnosis, language modeling, partially observable control, and cost-aware Bayesian experimental design show that NBSR achieves competitive predictive performance while providing transparent routing traces, path-dependent evidence attribution, uncertainty-aware decision control, and resource-rational inference. Overall, NBSR offers a mathematically grounded framework for interpretable, modular, and resource-rational agentic AI.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑