提出一种统一框架，用局部修正解决概率模型中的不一致问题。
Local Inconsistency Resolution: The Interplay between Attention and Control in Probabilistic Models
- 通过聚焦模型局部并控制参数来修复信念矛盾
- 能统一EM、信念传播、GAN等经典算法，且改进GFlowNet收敛性
- 适合研究概率推理与优化统一理论的学者
我们提出一种通用的学习与近似推理算法，具有直观的认知解释：迭代聚焦于模型的一部分，利用受控参数解决不一致问题。该框架称为局部不一致化解法（LIR），基于概率依赖图（PDGs），具备灵活表示能力，可捕捉不一致信念。我们证明LIR能统一并推广文献中多种重要算法，包括期望最大化（EM）、信念传播、对抗训练、GANs和GFlowNets。在后一情形中，LIR提出了更自然的损失函数，实验证明其可提升GFlowNet的收敛性。每种方法均可通过选择不同的聚焦机制（注意力与控制）作为LIR的特例恢复。我们在离散PDGs上实现该算法，对合成生成的PDGs进行实验，比较其行为与全图全局优化语义的差异。
原文摘要 · Abstract (English)
We present a generic algorithm for learning and approximate inference with an intuitive epistemic interpretation: iteratively focus on a subset of the model and resolve inconsistencies using the parameters under control. This framework, which we call Local Inconsistency Resolution (LIR) is built upon Probabilistic Dependency Graphs (PDGs), which provide a flexible representational foundation capable of capturing inconsistent beliefs. We show how LIR unifies and generalizes a wide variety of important algorithms in the literature, including the Expectation-Maximization (EM) algorithm, belief propagation, adversarial training, GANs, and GFlowNets. In the last case, LIR actually suggests a more natural loss, which we demonstrate improves GFlowNet convergence. Each method can be recovered as a specific instance of LIR by choosing a procedure to direct focus (attention and control). We implement this algorithm for discrete PDGs and study its properties on synthetically generated PDGs, comparing its behavior to the global optimization semantics of the full PDG.
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。