mlsanityData to 7 Oct 2026

Counterfactual Outcome Prediction using Structured State Space Model

arXiv 2305.09207 ↗First posted 16 May 2023cs.LG cs.AI stat.MEcited by 0

On the map: State-space sequence models (S4, Mamba) → Core SSM architectures for language

Abstract (arXiv)

Counterfactual outcome prediction in longitudinal data has recently gained attention due to its potential applications in healthcare and social sciences. In this paper, we explore the use of the state space model, a popular sequence model, for this task. Specifically, we compare the performance of two models: Treatment Effect Neural Controlled Differential Equation (TE-CDE) and structured state space model (S4Model). While TE-CDE uses controlled differential equations to address time-dependent confounding, it suffers from optimization issues and slow training. In contrast, S4Model is more efficient at modeling long-range dependencies and easier to train. We evaluate the models on a simulated lung tumor growth dataset and find that S4Model outperforms TE-CDE with 1.63x reduction in per epoch training time and 10x better normalized mean squared error. Additionally, S4Model is more stable during training and less sensitive to weight initialization than TE-CDE. Our results suggest that the state space model may be a promising approach for counterfactual outcome prediction in longitudinal data, with S4Model offering a more efficient and effective alternative to TE-CDE.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Core SSM architectures for language, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 5 of its 6 references that are in the map. First posted on arXiv 16 May 2023.

Builds on

5 of 6 references.

Closest ancestors · 1

Same direction, newest first

  1. 2021Efficiently Modeling Long Sequences with Structured State Spaces31 Oct

Other references · 4

  1. 2021Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layerscited by 607
  2. 2022Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equationscited by 59
  3. 2019Deep Compressed Sensingcited by 46
  4. 2021SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Datacited by 25

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Causal State-Space Model for Causal Inference: Estimating Longitudinal Individual Treatment Effects
  2. 2026Causal Diffusion Models for Counterfactual Outcome Distributions in Longitudinal Data
  3. 2023Counterfactual Generative Models for Time-Varying Treatments
  4. 2026DeepImagine: Clinical Trial Outcome Prediction via Stepwise Local Counterfactual Imaginations
  5. 2023A New Deep State-Space Analysis Framework for Patient Latent State Estimation and Classification from EHR Time Series Data
  6. 2025Flow-based Generative Modeling of Potential Outcomes and Counterfactuals
  7. 2025Flow IV: Counterfactual Inference In Nonseparable Outcome Models Using Instrumental Variables
  8. 2026From Static Risk to Dynamic Trajectories: Toward World-Model-Inspired Clinical Prediction