@inproceedings{20303,
  abstract     = {Observational genome-wide association studies are now widely used for causal inference in genetic epidemiology. To maintain privacy, such data is often only publicly available as summary statistics, and often studies for the endogenous covariates and the outcome are available separately. This has necessitated methods tailored to two-sample summary statistics. Current state-of-the-art methods modify linear instrumental variable (IV) regression---with genetic variants as instruments---to account for unmeasured confounding. However, since the endogenous covariates can be high dimensional, standard IV assumptions are generally insufficient to identify all causal effects simultaneously. We ensure identifiability by assuming the causal effects are sparse and propose a sparse causal effect two-sample IV estimator, spaceTSIV, adapting the spaceIV estimator by Pfister and Peters (2022) for two-sample summary statistics. We provide two methods, based on L0- and L1-penalization, respectively. We prove identifiability of the sparse causal effects in the two-sample setting and consistency of spaceTSIV. The performance of spaceTSIV is compared with existing two-sample IV methods in simulations. Finally, we showcase our methods using real proteomic and gene-expression data for drug-target discovery.},
  author       = {Huang, Shimeng and Pfister, Niklas and Bowden, Jack},
  booktitle    = {The 28th International Conference on Artificial Intelligence and Statistics},
  issn         = {2640-3498},
  location     = {Mai Khao, Thailand},
  pages        = {3394--3402},
  publisher    = {ML Research Press},
  title        = {{Sparse causal effect estimation using two-sample summary statistics in the presence of unmeasured confounding}},
  volume       = {258},
  year         = {2025},
}

@inproceedings{21068,
  abstract     = {Causal reasoning and discovery, two fundamental tasks of causal analysis,
often face challenges in applications due to the complexity, noisiness, and highdimensionality of real-world data. Despite recent progress in identifying latent
causal structures using causal representation learning (CRL), what makes learned
representations useful for causal downstream tasks and how to evaluate them are
still not well understood. In this paper, we reinterpret CRL using a measurement
model framework, where the learned representations are viewed as proxy measurements of the latent causal variables. Our approach clarifies the conditions under
which learned representations support downstream causal reasoning and provides
a principled basis for quantitatively assessing the quality of representations using
a new Test-based Measurement EXclusivity (T-MEX) score. We validate T-MEX
across diverse causal inference scenarios, including numerical simulations and
real-world ecological video analysis, demonstrating that the proposed framework
and corresponding score effectively assess the identification of learned representations and their usefulness for causal downstream tasks. Reproducible code can
be found at https://github.com/shimenghuang/a-measurement-perspective-of-crl.},
  author       = {Yao, Dingling and Huang, Shimeng and Cadei, Riccardo and Zhang, Kun and Locatello, Francesco},
  booktitle    = {39th Annual Conference on Neural Information Processing Systems},
  issn         = {1049-5258},
  location     = {San Diego, CA, United States},
  publisher    = {Neural Information Processing Systems Foundation},
  title        = {{The third pillar of causal analysis? A measurement perspective on causal representations}},
  doi          = {10.52202/085713-1444},
  volume       = {38},
  year         = {2025},
}