paper-with-me

홈 › Papers

Sample Complexity of Causal Identification with Temporal Heterogeneity

2026-02-06 · Ameya Rathod, Sujay Belsare, Salvik Krishna Nautiyal, Dhruv Laad, Ponnurangam Kumaraguru arxiv

Recovering a unique causal graph from observational data is an ill-posed problem because multiple generating mechanisms can lead to the same observational distribution. This problem becomes solvable only by exploiting specific structural or distributional assumptions. While recent work has separately utilized time-series dynamics or multi-environment heterogeneity to constrain this problem, we integrate both as complementary sources of heterogeneity. This integration yields unified necessary identifiability conditions and enables a rigorous analysis of the statistical limits of recovery under thin versus heavy-tailed noise. In particular, temporal structure is shown to effectively substitute for missing environmental diversity, possibly achieving identifiability even under insufficient heterogeneity. Extending this analysis to heavy-tailed (Student's t) distributions, we demonstrate that while geometric identifiability conditions remain invariant, the sample complexity diverges significantly from the Gaussian baseline. Explicit information-theoretic bounds quantify this cost of robustness, establishing the fundamental limits of covariance-based causal graph recovery methods in realistic non-stationary systems. This work shifts the focus from whether causal structure is identifiable to whether it is statistically recoverable in practice.

📄 PDF Abstract BibTeX arXiv:2602.06899

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Structural DID with ML: Theory, Simulation, and a Roadmap for Applied Research

2025-07-21 · Yile Yu, Anzhi Xu, Yi Wang arxiv

Causal inference in observational panel data has become a central concern in economics,policy analysis,and the broader social sciences.To address the core contradiction where traditional difference-in-differences (DID) s…

Causal Inference

Targeting relative risk heterogeneity with causal forests

2023-09-26 · Vik Shirvaikar, Andrea Storås, Xi Lin, Chris Holmes

The identification of heterogeneous treatment effects (HTE) across subgroups is of significant interest in clinical trial analysis. Several state-of-the-art HTE estimation methods, including causal forests, apply recursi…

Exploiting Heterogeneity in Robust Federated Best-Arm Identification

2021-09-13 · Aritra Mitra, Hamed Hassani, George Pappas

We study a federated variant of the best-arm identification problem in stochastic multi-armed bandits: a set of clients, each of whom can sample only a subset of the arms, collaborate via a server to identify the best ar…

Multi-Armed Bandits

Doubly cross-fit debiased machine learning of heterogeneous treatment effects under principal stratification

2026-06-27 · Jiaqi Tong, Fan Li arxiv

Principal stratification provides a foundational framework for causal inference with intermediate outcomes by defining causal effects within subpopulations, yet existing work has largely focused on average effects across…

Causal Inference

Causality-inspired Federated Learning for Dynamic Spatio-Temporal Graphs

2026-03-31 · Yuxuan Liu, Wenchao Xu, Haozhao Wang, Zhiming He 외 arxiv

Federated Graph Learning (FGL) has emerged as a powerful paradigm for decentralized training of graph neural networks while preserving data privacy. However, existing FGL methods are predominantly designed for static gra…

Contrastive LearningFederated LearningGraph Learning