解决多处理场景下因果效应估计的权重选择与高维计算难题。
Causal Representation Learning with Optimal Compression under Complex Treatments
- 提出最优平衡权重理论解法，避免繁琐调参。
- 处理组合策略在高维下仍保持线性可扩展性。
- 适合大规模干预分析，尤其图像数据场景。
在多处理场景中估计个体处理效应（ITE）面临两大挑战：平衡权重的超参数选择困境与计算可扩展性的维度诅咒。本文推导了多处理情形下的新泛化界，并提出理论上的最优平衡权重 α 估计器，消除了昂贵的启发式调参。研究了三种平衡策略：成对、一对多（OVA）和处理聚合。尽管 OVA 在低维设置中表现更优，但所提出的处理聚合方法在处理空间扩大时仍能保证准确性和 O(1) 的可扩展性。此外，将框架扩展至生成架构——多处理因果EGM，保留了处理流形的 Wasserstein 测地结构。在半合成与图像数据集上的实验表明，该方法在估计精度和效率上显著优于传统模型，尤其在大规模干预场景中表现突出。
原文摘要 · Abstract (English)
Estimating Individual Treatment Effects (ITE) in multi-treatment scenarios faces two critical challenges: the Hyperparameter Selection Dilemma for balancing weights and the Curse of Dimensionality in computational scalability. This paper derives a novel multi-treatment generalization bound and proposes a theoretical estimator for the optimal balancing weight $α$, eliminating expensive heuristic tuning. We investigate three balancing strategies: Pairwise, One-vs-All (OVA), and Treatment Aggregation. While OVA achieves superior precision in low-dimensional settings, our proposed Treatment Aggregation ensures both accuracy and O(1) scalability as the treatment space expands. Furthermore, we extend our framework to a generative architecture, Multi-Treatment CausalEGM, which preserves the Wasserstein geodesic structure of the treatment manifold. Experiments on semi-synthetic and image datasets demonstrate that our approach significantly outperforms traditional models in estimation accuracy and efficiency, particularly in large-scale intervention scenarios.
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。