Orthogonal Representation Learning for Estimating Causal Quantities

[2502.04274] Orthogonal Representation Learning for Estimating Causal Quantities Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Machine Learning arXiv:2502.04274 (cs) [Submitted on 6 Feb 2025 ( v1 ), last revised 27 Apr 2026 (this version, v4)] Title: Orthogonal Representation Learning for Estimating Causal Quantities Authors: Valentyn Melnychuk , Dennis Frauen , Jonas Schweisthal , Stefan Feuerriegel View a PDF of the paper titled Orthogonal Representation Learning for Estimating Causal Quantities, by Valentyn Melnychuk and 3 other authors View PDF HTML (experimental) Abstract: End-to-end representation learning has become a powerful tool for estimating causal quantities from high-dimensional observational data, but its efficiency remained unclear. Here, we face a central tension: End-to-end representation learning methods often work well in practice but lack asymptotic optimality in the form of the quasi-oracle efficiency. In contrast, two-stage Neyman-orthogonal learners provide such a theoretical optimality property but do not explicitly benefit from the strengths of representation learning. In this work, we step back and ask two research questions: (1) When do representations strengthen existing Neyman-orthogonal learners? and (2) Can a balancing constraint - a commonly proposed technique in the representation learning literature - provide improvements to Neyman-orthogonality? We address these two questions through our theoretical and empirical analysis, where we introduce a unifying framework that connects representation learning with Neyman-orthogonal learners (namely, OR-learners). In particular, we show that, under the low-dimensional manifold hypothesis, the OR-learners can strictly improve the estimation error of the standard Neyman-orthogonal learners. At the same time, we find that the balancing constraint requires an additional inductive bias and cannot generally compensate for the lack of Neyman-orthogonality of the end-to-end approaches. Building on these insights, we offer guidelines for how users can effectively combine representation learning with the classical Neyman-orthogonal learners to achieve both practical performance and theoretical guarantees. Subjects: Machine Learning (cs.LG) Cite as: arXiv:2502.04274 [cs.LG] (or arXiv:2502.04274v4 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2502.04274 Focus to learn more arXiv-issued DOI via DataCite Journal reference: Proceedings of the 29th International Conference on Artificial Intelligence and Statistics (AISTATS) 2026, Tangier, Morocco Submission history From: Valentyn Melnychuk [ view email ] [v1] Thu, 6 Feb 2025 18:18:48 UTC (1,982 KB) [v2] Fri, 10 Oct 2025 17:15:56 UTC (2,504 KB) [v3] Wed, 8 Apr 2026 19:53:59 UTC (2,501 KB) [v4] Mon, 27 Apr 2026 00:11:00 UTC (2,898 KB) Full-text links: Access Paper: View a PDF of the paper titled Orthogonal Representation Learning for Estimating Causal Quantities, by Valentyn Melnychuk and 3 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG < prev | next > new | recent | 2025-02 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Bridging Generative and Discriminative Noisy-Label Learning via Direction-Agnostic EM Formulation#1116049
• Bayesian Symbolic Regression with Entropic Reinforcement Learning#441810
• Matrix-Product Belief Propagation for continuous-state-space variables#1141538
• Toward nonlinear representations with Gaussian-splat manifolds for physics-informed learning.#785403
• Learning POMDP World Models from Observations with Language-Model Priors#180661