Deep Learning of Continuous and Structured Policies for Aggregated Heterogeneous Treatment Effects

• URL: http://arxiv.org/abs/2507.05511v1
• Date: Mon, 07 Jul 2025 22:14:24 GMT
• Title: Deep Learning of Continuous and Structured Policies for Aggregated Heterogeneous Treatment Effects
• Authors: Jennifer Y. Zhang, Shuyang Du, Will Y. Zou,
• Abstract summary: We derive a formulation for incorporating multiple treatment policy variables into the functional forms of individual and average treatment effects.<n>We then develop a methodology to directly rank subjects using aggregated HTE functions.<n>Together, these algorithms build towards a generic framework for deep learning of heterogeneous treatment policies.
• Score: 0.7100520098029438
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: As estimation of Heterogeneous Treatment Effect (HTE) is increasingly adopted across a wide range of scientific and industrial applications, the treatment action space can naturally expand, from a binary treatment variable to a structured treatment policy. This policy may include several policy factors such as a continuous treatment intensity variable, or discrete treatment assignments. From first principles, we derive the formulation for incorporating multiple treatment policy variables into the functional forms of individual and average treatment effects. Building on this, we develop a methodology to directly rank subjects using aggregated HTE functions. In particular, we construct a Neural-Augmented Naive Bayes layer within a deep learning framework to incorporate an arbitrary number of factors that satisfies the Naive Bayes assumption. The factored layer is then applied with continuous treatment variables, treatment assignment, and direct ranking of aggregated treatment effect functions. Together, these algorithms build towards a generic framework for deep learning of heterogeneous treatment policies, and we show their power to improve performance with public datasets.

Related papers

• Policy Learning for Optimal Dynamic Treatment Regimes with Observational Data [0.0]
  We study the statistical learning of optimal dynamic treatment regimes (DTRs) that determine the optimal treatment assignment for each individual at each stage based on their evolving history.
  arXiv  Detail & Related papers  (2024-03-30T02:33:39Z)
• Asymptotic Inference for Multi-Stage Stationary Treatment Policy with Variable Selection [13.202945240520986]
  Dynamic treatment regimes or policies are a sequence of decision functions over multiple stages that are tailored to individual features.<n>One important class of treatment policies in practice, namely multi-stage stationary treatment policies, prescribes treatment assignment using the same decision function across stages.<n>Although there has been extensive literature on constructing valid inference for the value function associated with dynamic treatment policies, little work has focused on the policies themselves.
  arXiv  Detail & Related papers  (2023-01-29T22:00:53Z)
• Synthetic Blip Effects: Generalizing Synthetic Controls for the Dynamic Treatment Regime [31.194595148880573]
  We consider the estimation of unit-specific treatment effects from panel data collected via a dynamic treatment regime. We propose an identification strategy for any unit-specific mean outcome under any sequence of interventions.
  arXiv  Detail & Related papers  (2022-10-20T04:11:20Z)
• Transfer Learning on Heterogeneous Feature Spaces for Treatment Effects Estimation [103.55894890759376]
  This paper introduces several building blocks that use representation learning to handle the heterogeneous feature spaces. We show how these building blocks can be used to recover transfer learning equivalents of the standard CATE learners.
  arXiv  Detail & Related papers  (2022-10-08T16:41:02Z)
• Causal Modeling of Policy Interventions From Sequences of Treatments and Outcomes [5.107614397012659]
  Data-driven decision-making requires the ability to predict what happens if a policy is changed. Existing methods that predict how the outcome evolves assume that the tentative sequences of future treatments are fixed in advance. In practice, the treatments are determinedally by a policy and may depend on the efficiency of previous treatments.
  arXiv  Detail & Related papers  (2022-09-09T06:50:37Z)
• Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability [82.29775890542967]
  Estimating personalized effects of treatments is a complex, yet pervasive problem. Recent developments in the machine learning literature on heterogeneous treatment effect estimation gave rise to many sophisticated, but opaque, tools. We use post-hoc feature importance methods to identify features that influence the model's predictions.
  arXiv  Detail & Related papers  (2022-06-16T17:59:05Z)
• Can Transformers be Strong Treatment Effect Estimators? [86.32484218657166]
  We develop a general framework based on the Transformer architecture to address a variety of treatment effect estimation problems. Our methods are applied to discrete, continuous, structured, or dosage-associated treatments. Our experiments with Transformers as Treatment Effect Estimators (TransTEE) demonstrate that these inductive biases are also effective on the sorts of estimation problems and datasets that arise in research aimed at estimating causal effects.
  arXiv  Detail & Related papers  (2022-02-02T23:56:42Z)
• Disentangled Counterfactual Recurrent Networks for Treatment Effect Inference over Time [71.30985926640659]
  We introduce the Disentangled Counterfactual Recurrent Network (DCRN), a sequence-to-sequence architecture that estimates treatment outcomes over time. With an architecture that is completely inspired by the causal structure of treatment influence over time, we advance forecast accuracy and disease understanding. We demonstrate that DCRN outperforms current state-of-the-art methods in forecasting treatment responses, on both real and simulated data.
  arXiv  Detail & Related papers  (2021-12-07T16:40:28Z)
• SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data [83.50281440043241]
  We study the problem of inferring heterogeneous treatment effects from time-to-event data. We propose a novel deep learning method for treatment-specific hazard estimation based on balancing representations.
  arXiv  Detail & Related papers  (2021-10-26T20:13:17Z)
• On Inductive Biases for Heterogeneous Treatment Effect Estimation [91.3755431537592]
  We investigate how to exploit structural similarities of an individual's potential outcomes (POs) under different treatments. We compare three end-to-end learning strategies to overcome this problem.
  arXiv  Detail & Related papers  (2021-06-07T16:30:46Z)
• Learning Continuous Treatment Policy and Bipartite Embeddings for Matching with Heterogeneous Causal Effects [8.525061716196424]
  Current methods make binary yes-or-no decisions based on the treatment effect of a single outcome dimension. We propose to formulate the effectiveness of treatment as a parametrizable model, expanding to a multitude of treatment intensities and complexities. We utilize deep learning to optimize the desired holistic metric space instead of predicting single-dimensional treatment counterfactual.
  arXiv  Detail & Related papers  (2020-04-21T01:36:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.