arXiv cs.AI· Ryo Kamimura, Thong Pham·· 13 小时前AI 评分24
LRQS：基于变换低秩分位数曲面的因果发现方法
Causal Discovery via Transformed Low-Rank Quantile Surfaces
AI 导读
研究者提出双变量因果模型 LRQS（Low-Rank Quantile Surfaces），在因果方向上条件分位数曲面的未知单调变换可做低秩函数分解，并证明了该模型的通用可识别性。LRQS 涵盖位置-尺度噪声模型与后非线性异方差噪声模型，支持多个分位数基以刻画超出位置-尺度效应的分布变化。实验显示其在条件分布形状变化或观测失真超出既有假设时尤为有效，该工作已被 NeurIPS 2026 接收。
正文 · 原文
Abstract:We propose Low-Rank Quantile Surfaces (LRQS), a bivariate causal model in which, in the causal direction, an unknown monotone transformation of the conditional quantile surface admits a low-rank functional decomposition. LRQS subsumes location-scale noise models and post-nonlinear heteroscedastic noise models, while allowing multiple quantile bases to represent changes beyond location-scale effects. We prove generic identifiability of LRQS: the transformed quantile surface is low rank in the causal direction, whereas reverse representability under the corresponding constraints occurs only for exceptional, fine-tuned cause marginals. We provide a nonparametric causal score using a fitting procedure that alternates between rank-constrained approximation of discretized quantile surfaces and isotonic estimation of the unknown monotone transformation. Experiments on synthetic mechanisms with higher-rank distributional shape variation and strong nonlinear distortions, together with standard bivariate benchmarks, show that LRQS is especially effective when conditional distributional shape or observation distortion goes beyond existing location-scale assumptions.
| Comments: | Accepted at NeurIPS 2026 |
| Subjects: | Methodology (stat.ME); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Machine Learning (stat.ML) |
| Cite as: | arXiv:2609.16931 [stat.ME] |
| (or arXiv:2609.16931v2 [stat.ME] for this version) | |
| https://doi.org/10.48550/arXiv.2609.16931 arXiv-issued DOI via DataCite |
Submission history
From: Thong Pham [view email]
[v1]
Tue, 15 Sep 2026 10:06:19 UTC (481 KB)
[v2]
Wed, 21 Oct 2026 08:46:44 UTC (491 KB)
来源：arXiv cs.AI · arxiv.org