[{"date_created":"2025-09-07T22:01:35Z","OA_type":"green","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","oa":1,"main_file_link":[{"url":"https://doi.org/10.48550/arXiv.2410.12300","open_access":"1"}],"year":"2025","_id":"20303","quality_controlled":"1","arxiv":1,"abstract":[{"text":"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.","lang":"eng"}],"publication_status":"published","date_updated":"2025-09-09T07:47:13Z","conference":{"end_date":"2025-05-05","start_date":"2025-05-03","location":"Mai Khao, Thailand","name":"AISTATS: Conference on Artificial Intelligence and Statistics"},"publication":"The 28th International Conference on Artificial Intelligence and Statistics","publisher":"ML Research Press","language":[{"iso":"eng"}],"intvolume":"       258","title":"Sparse causal effect estimation using two-sample summary statistics in the presence of unmeasured confounding","publication_identifier":{"eissn":["2640-3498"]},"external_id":{"arxiv":["2410.12300"]},"page":"3394-3402","OA_place":"repository","scopus_import":"1","acknowledgement":"The authors would like to thank Stephen Burgess and Ashish Patel for helpful discussions at\r\nthe start of this research project, and Anton Rask Lundborg for helpful discussions on the\r\nuniform asymptotic results. This work was partially completed during SH’s research visit at\r\nNovo Nordisk. The authors would like to thank Jesper Ferkinghoff-Borg, Kang Li and Lewis\r\nMarsh for facilitating this visit and for discussing necessary concepts and tools in statistical\r\ngenetics at an early stage. SH and NP are supported by a research grant (0069071) from Novo\r\nNordisk Fonden. JB is funded at the University of Exeter by research grant MR/X011372/1.","article_processing_charge":"No","status":"public","date_published":"2025-05-01T00:00:00Z","oa_version":"Preprint","month":"05","day":"01","author":[{"orcid":"0000-0001-6919-821X","full_name":"Huang, Shimeng","first_name":"Shimeng","id":"989c2a06-fb4e-11ef-a992-ab766442255b","last_name":"Huang"},{"full_name":"Pfister, Niklas","last_name":"Pfister","first_name":"Niklas"},{"last_name":"Bowden","first_name":"Jack","full_name":"Bowden, Jack"}],"type":"conference","department":[{"_id":"FrLo"}],"citation":{"ieee":"S. Huang, N. Pfister, and J. Bowden, “Sparse causal effect estimation using two-sample summary statistics in the presence of unmeasured confounding,” in <i>The 28th International Conference on Artificial Intelligence and Statistics</i>, Mai Khao, Thailand, 2025, vol. 258, pp. 3394–3402.","mla":"Huang, Shimeng, et al. “Sparse Causal Effect Estimation Using Two-Sample Summary Statistics in the Presence of Unmeasured Confounding.” <i>The 28th International Conference on Artificial Intelligence and Statistics</i>, vol. 258, ML Research Press, 2025, pp. 3394–402.","ama":"Huang S, Pfister N, Bowden J. Sparse causal effect estimation using two-sample summary statistics in the presence of unmeasured confounding. In: <i>The 28th International Conference on Artificial Intelligence and Statistics</i>. Vol 258. ML Research Press; 2025:3394-3402.","apa":"Huang, S., Pfister, N., &#38; Bowden, J. (2025). Sparse causal effect estimation using two-sample summary statistics in the presence of unmeasured confounding. In <i>The 28th International Conference on Artificial Intelligence and Statistics</i> (Vol. 258, pp. 3394–3402). Mai Khao, Thailand: ML Research Press.","ista":"Huang S, Pfister N, Bowden J. 2025. Sparse causal effect estimation using two-sample summary statistics in the presence of unmeasured confounding. The 28th International Conference on Artificial Intelligence and Statistics. AISTATS: Conference on Artificial Intelligence and Statistics, PMLR, vol. 258, 3394–3402.","chicago":"Huang, Shimeng, Niklas Pfister, and Jack Bowden. “Sparse Causal Effect Estimation Using Two-Sample Summary Statistics in the Presence of Unmeasured Confounding.” In <i>The 28th International Conference on Artificial Intelligence and Statistics</i>, 258:3394–3402. ML Research Press, 2025.","short":"S. Huang, N. Pfister, J. Bowden, in:, The 28th International Conference on Artificial Intelligence and Statistics, ML Research Press, 2025, pp. 3394–3402."},"volume":258,"alternative_title":["PMLR"]},{"month":"12","related_material":{"link":[{"url":"https://github.com/shimenghuang/a-measurement-perspective-of-crl","relation":"software"}]},"day":"15","oa_version":"Preprint","article_processing_charge":"No","date_published":"2025-12-15T00:00:00Z","status":"public","volume":38,"alternative_title":["Advances in Neural Information Processing Systems"],"department":[{"_id":"FrLo"}],"citation":{"ista":"Yao D, Huang S, Cadei R, Zhang K, Locatello F. 2025. The third pillar of causal analysis? A measurement perspective on causal representations. 39th Annual Conference on Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems, Advances in Neural Information Processing Systems, vol. 38.","apa":"Yao, D., Huang, S., Cadei, R., Zhang, K., &#38; Locatello, F. (2025). The third pillar of causal analysis? A measurement perspective on causal representations. In <i>39th Annual Conference on Neural Information Processing Systems</i> (Vol. 38). San Diego, CA, United States: Neural Information Processing Systems Foundation.","short":"D. Yao, S. Huang, R. Cadei, K. Zhang, F. Locatello, in:, 39th Annual Conference on Neural Information Processing Systems, Neural Information Processing Systems Foundation, 2025.","chicago":"Yao, Dingling, Shimeng Huang, Riccardo Cadei, Kun Zhang, and Francesco Locatello. “The Third Pillar of Causal Analysis? A Measurement Perspective on Causal Representations.” In <i>39th Annual Conference on Neural Information Processing Systems</i>, Vol. 38. Neural Information Processing Systems Foundation, 2025.","mla":"Yao, Dingling, et al. “The Third Pillar of Causal Analysis? A Measurement Perspective on Causal Representations.” <i>39th Annual Conference on Neural Information Processing Systems</i>, vol. 38, Neural Information Processing Systems Foundation, 2025.","ieee":"D. Yao, S. Huang, R. Cadei, K. Zhang, and F. Locatello, “The third pillar of causal analysis? A measurement perspective on causal representations,” in <i>39th Annual Conference on Neural Information Processing Systems</i>, San Diego, CA, United States, 2025, vol. 38.","ama":"Yao D, Huang S, Cadei R, Zhang K, Locatello F. The third pillar of causal analysis? A measurement perspective on causal representations. In: <i>39th Annual Conference on Neural Information Processing Systems</i>. Vol 38. Neural Information Processing Systems Foundation; 2025."},"type":"conference","author":[{"full_name":"Yao, Dingling","id":"d3e02e50-48a8-11ee-8f62-c108061797fa","first_name":"Dingling","last_name":"Yao"},{"last_name":"Huang","id":"989c2a06-fb4e-11ef-a992-ab766442255b","first_name":"Shimeng","full_name":"Huang, Shimeng","orcid":"0000-0001-6919-821X"},{"first_name":"Riccardo","id":"0fa8b76f-72f0-11ef-b75a-a5da96e5ad6b","last_name":"Cadei","full_name":"Cadei, Riccardo"},{"full_name":"Zhang, Kun","first_name":"Kun","last_name":"Zhang"},{"orcid":"0000-0002-4850-0683","full_name":"Locatello, Francesco","first_name":"Francesco","id":"26cfd52f-2483-11ee-8040-88983bcc06d4","last_name":"Locatello"}],"OA_place":"repository","external_id":{"arxiv":["2505.17708"]},"title":"The third pillar of causal analysis? A measurement perspective on causal representations","publication_identifier":{"issn":["1049-5258"]},"intvolume":"        38","acknowledgement":"This research was funded in whole or in part by the Austrian Science Fund (FWF) 10.55776/COE12. For open access purposes, the author has applied a CC BY public copyright license to any accepted manuscript version arising from this submission.\r\n","tmp":{"short":"CC BY (4.0)","image":"/images/cc_by.png","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode"},"abstract":[{"text":"Causal reasoning and discovery, two fundamental tasks of causal analysis,\r\noften face challenges in applications due to the complexity, noisiness, and highdimensionality of real-world data. Despite recent progress in identifying latent\r\ncausal structures using causal representation learning (CRL), what makes learned\r\nrepresentations useful for causal downstream tasks and how to evaluate them are\r\nstill not well understood. In this paper, we reinterpret CRL using a measurement\r\nmodel framework, where the learned representations are viewed as proxy measurements of the latent causal variables. Our approach clarifies the conditions under\r\nwhich learned representations support downstream causal reasoning and provides\r\na principled basis for quantitatively assessing the quality of representations using\r\na new Test-based Measurement EXclusivity (T-MEX) score. We validate T-MEX\r\nacross diverse causal inference scenarios, including numerical simulations and\r\nreal-world ecological video analysis, demonstrating that the proposed framework\r\nand corresponding score effectively assess the identification of learned representations and their usefulness for causal downstream tasks. Reproducible code can\r\nbe found at https://github.com/shimenghuang/a-measurement-perspective-of-crl.","lang":"eng"}],"publication_status":"published","arxiv":1,"quality_controlled":"1","ddc":["000"],"publisher":"Neural Information Processing Systems Foundation","language":[{"iso":"eng"}],"publication":"39th Annual Conference on Neural Information Processing Systems","corr_author":"1","date_updated":"2026-07-28T07:14:27Z","conference":{"end_date":"2025-12-07","start_date":"2025-12-02","location":"San Diego, CA, United States","name":"NeurIPS: Neural Information Processing Systems"},"oa":1,"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","das_tickbox":"1","OA_type":"green","has_accepted_license":"1","date_created":"2026-01-29T14:24:56Z","_id":"21068","year":"2025","main_file_link":[{"open_access":"1","url":"https://doi.org/10.48550/arXiv.2505.17708"}]}]