aiqbench analysis
This paper introduces DR-FRL, a novel framework that adapts doubly robust causal estimators to handle irregular longitudinal data streams like sensor logs and lab values without reducing them to scalar summaries. By aligning functional encoders with the efficient influence function, it ensures asymptotic linearity even under high-dimensional confounding or weak support conditions typical of real-world clinical settings. Simulations confirm performance gains in complex scenarios, though an audit suggests that for specific ICU endpoints, standard scalar summaries may already capture sufficient information.
Doubly Robust Functional Representation Learning for Longitudinal Causal Inference with Irregular Histories
arXiv:2607.28567v1 Announce Type: cross Abstract: Longitudinal causal studies often record histories as irregular functional fragments: laboratory values, physiologic signals, sensor streams, and image-derived summaries measured at unequal and informative times. Standard doubly robust estimators usually require scalar summaries, whereas sequence learners optimize prediction losses that need not stabilize the efficient influence function. We propose Doubly Robust Functional Representation Learning (DR-FRL), a cross-fitted workflow that turns irregular histories into estimand-targeted states for observed-history regimes. Functional and temporal encoders map point clouds and prior histories into states; nuisance heads estimate outcome, treatment, and censoring functions; and EIF-targeted validation, calibration, overlap, tail, and ablation diagnostics assess whether the state supports the estimating equation. If the selected state preserves the nuisance information needed by the EIF, representation error enters the same second-order product remainder as ordinary nuisance error, and the mean estimator is asymptotically linear under explicit rate, overlap, calibration, and stability conditions. Catoni aggregation is treated separately as a bounded-influence point estimator, not a replacement for Wald inference. Simulations show gains when functional confounding is high-dimensional, measurement is informative, support is weak, or pseudo-outcomes are heavy-tailed. A VitalDB audit shows that DR-FRL can use irregular laboratory point clouds and deliver a useful negative finding: for this ICU-disposition endpoint, scalar laboratory summaries already carry much endpoint-relevant information.
Abstract:Longitudinal causal studies often record histories as irregular functional fragments: laboratory values, physiologic signals, sensor streams, and image-derived summaries measured at unequal and informative times. Standard doubly robust estimators usually require scalar summaries, whereas sequence learners optimize prediction losses that need not stabilize the efficient influence function. We propose Doubly Robust Functional Representation Learning (DR-FRL), a cross-fitted workflow that turns irregular histories into estimand-targeted states for observed-history regimes. Functional and temporal encoders map point clouds and prior histories into states; nuisance heads estimate outcome, treatment, and censoring functions; and EIF-targeted validation, calibration, overlap, tail, and ablation diagnostics assess whether the state supports the estimating equation. If the selected state preserves the nuisance information needed by the EIF, representation error enters the same second-order product remainder as ordinary nuisance error, and the mean estimator is asymptotically linear under explicit rate, overlap, calibration, and stability conditions. Catoni aggregation is treated separately as a bounded-influence point estimator, not a replacement for Wald inference. Simulations show gains when functional confounding is high-dimensional, measurement is informative, support is weak, or pseudo-outcomes are heavy-tailed. A VitalDB audit shows that DR-FRL can use irregular laboratory point clouds and deliver a useful negative finding: for this ICU-disposition endpoint, scalar laboratory summaries already carry much endpoint-relevant information.
Machine Learning (stat.ML); Machine Learning (cs.LG); Applications (stat.AP); Computation (stat.CO); Methodology (stat.ME)
arXiv:2607.28567 [stat.ML]
(or arXiv:2607.28567v1 [stat.ML] for this version)
https://doi.org/10.48550/arXiv.2607.28567 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
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.
Full text under the publisher's open licence · 311 words
Related coverage
Causal Bayesian Optimization: Foundations, Methods, and Applications
arXiv · Sep 22, 2026
Learning the Constitutive Behavior of Materials via Neural Operators and Causal Attention: Case Studies in Plasticity and Damage
arXiv · Sep 3, 2026
DAG-FM: A Foundation Model for Causal Discovery under Heterogeneous Causal Mechanisms
arXiv · Aug 4, 2026
J++ Lens: Jacobian Filtering Enables More Faithful Workspace Lenses
LessWrong · Oct 8, 2026