用神经网络学习条件最优传输映射，支持多类型条件输入。
Neural Conditional Transport Maps
- 通过超网络生成传输层参数，实现自适应映射
- 在敏感性分析中高效计算基于OT的敏感性指标
- 适用于生成建模与黑箱模型可解释性等场景
我们提出一种神经框架，用于学习概率分布之间的条件最优传输（OT）映射。该方法引入一个可同时处理分类与连续条件变量的条件机制。核心是基于输入条件生成传输层参数的超网络，构建出优于简单条件方法的自适应映射。全面的消融实验验证了该方法相较于基线配置的优越性能。此外，我们展示了其在全局敏感性分析中的应用，能高效计算基于OT的敏感性指数。本工作推动了条件最优传输的前沿进展，使最优传输原理可广泛应用于生成建模与黑箱模型可解释性等高维复杂领域。
原文摘要 · Abstract (English)
We present a neural framework for learning conditional optimal transport (OT) maps between probability distributions. Our approach introduces a conditioning mechanism capable of processing both categorical and continuous conditioning variables simultaneously. At the core of our method lies a hypernetwork that generates transport layer parameters based on these inputs, creating adaptive mappings that outperform simpler conditioning methods. Comprehensive ablation studies demonstrate the superior performance of our method over baseline configurations. Furthermore, we showcase an application to global sensitivity analysis, offering high performance in computing OT-based sensitivity indices. This work advances the state-of-the-art in conditional optimal transport, enabling broader application of optimal transport principles to complex, high-dimensional domains such as generative modeling and black-box model explainability.
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。