用电流类比概率迁移，实现离散数据生成的理论新方法。
Electric Currents for Discrete Data Generation
- 用电路电流类比概率流动，通过神经网络学习电流路径。
- 理论保证从源分布到目标分布的可证明概率转移。
- 适合对离散生成机制有理论探索需求的研究者。
我们提出一种名为电流传导离散数据生成（ECD²G）的新方法，该方法基于电工程理论，在离散数据生成中建立创新范式。将源分布样本视为电路中的电流输入节点，目标分布样本视为输出节点，利用神经网络学习电路中的电流传导路径以表示概率流动。通过沿学习到的电流路径传输源分布采样，实现从源分布到目标分布的有效映射，该过程具有理论上的可证明性保障。我们通过概念验证实验展示了该方法的可行性。
原文摘要 · Abstract (English)
We propose $\textbf{E}$lectric $\textbf{C}$urrent $\textbf{D}$iscrete $\textbf{D}$ata $\textbf{G}$eneration (ECD$^{2}$G), a pioneering method for data generation in discrete settings that is grounded in electrical engineering theory. Our approach draws an analogy between electric current flow in a circuit and the transfer of probability mass between data distributions. We interpret samples from the source distribution as current input nodes of a circuit and samples from the target distribution as current output nodes. A neural network is then used to learn the electric currents to represent the probability flow in the circuit. To map the source distribution to the target, we sample from the source and transport these samples along the circuit pathways according to the learned currents. This process provably guarantees transfer between data distributions. We present proof-of-concept experiments to illustrate our ECD$^{2}$G method.
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。