mlsanityData to 7 Oct 2026

Provably Efficient Neural Estimation of Structural Equation Model: An Adversarial Approach

arXiv 2007.01290 ↗First posted 2 Jul 2020stat.ML cs.LGcited by 31

Not on the map. Why?

Abstract (arXiv)

Structural equation models (SEMs) are widely used in sciences, ranging from economics to psychology, to uncover causal relationships underlying a complex system under consideration and estimate structural parameters of interest. We study estimation in a class of generalized SEMs where the object of interest is defined as the solution to a linear operator equation. We formulate the linear operator equation as a min-max game, where both players are parameterized by neural networks (NNs), and learn the parameters of these neural networks using the stochastic gradient descent. We consider both 2-layer and multi-layer NNs with ReLU activation functions and prove global convergence in an overparametrized regime, where the number of neurons is diverging. The results are established using techniques from online learning and local linearization of NNs, and improve in several aspects the current state-of-the-art. For the first time we provide a tractable estimation procedure for SEMs based on NNs with provable convergence and without the need for sample splitting.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 5; 2023: 2; 2024: 6; 2025: 5; 2026: 2.

31 papers.

Sort:

By area:

  1. 2021Proximal Causal Learning with Kernels: Two-Stage Estimation and Moment Restrictioncited by 54
  2. 2021Causal Inference Under Unmeasured Confounding With Negative Controls: A Minimax Learning Approachcited by 43
  3. 2021Proximal Reinforcement Learning: Efficient Off-Policy Evaluation in Partially Observed Markov Decision Processescited by 40
  4. 2021Deep Proxy Causal Learning and its Application to Confounded Bandit Policy Evaluationcited by 39
  5. 2021Instrumental Variable Value Iteration for Causal Offline Reinforcement Learningcited by 35
  6. 2021An Adaptive Stochastic Sequential Quadratic Programming with Differentiable Exact Augmented Lagrangianscited by 25
  7. 2021On Instrumental Variable Regression for Deep Offline Policy Evaluationcited by 22
  8. 2021Minimax Kernel Machine Learning for a Class of Doubly Robust Functionals with Application to Proximal Causal Inferencecited by 20
  9. 2023Minimax Instrumental Variable Regression and L2 Convergence Guarantees without Identification or Closednesscited by 13
  10. 2022Inference on Strongly Identified Functionals of Weakly Identified Functionscited by 12
  11. 2022Spectral Representation Learning for Conditional Moment Modelscited by 12
  12. 2024Spectral Representation for Causal Estimation with Hidden Confounderscited by 12
19 more
  1. 2022Instrumental Variables in Causal Inference and Machine Learning: A Surveycited by 10
  2. 2023Source Condition Double Robust Inference on Functionals of Inverse Problemscited by 8
  3. 2021Learning Causal Models from Conditional Moment Restrictions by Importance Weightingcited by 7
  4. 2024Nonparametric Instrumental Regression via Kernel Methods is Minimax Optimalcited by 7
  5. 2022Fast Instrument Learning with Faster Ratescited by 6
  6. 2024Nonparametric Instrumental Variable Regression through Stochastic Approximate Gradientscited by 6
  7. 2024Stochastic Optimization Algorithms for Instrumental Variable Regression with Streaming Datacited by 4
  8. 2024Targeted Sequential Indirect Experiment Designcited by 4
  9. 2025Demystifying Spectral Feature Learning for Instrumental Variable Regressioncited by 4
  10. 2024Causal Inference with Complex Treatments: A Surveycited by 3
  11. 2025Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regressioncited by 3
  12. 2021Instrument Space Selection for Kernel Maximum Moment Restrictioncited by 2
  13. 2025Outcome-Aware Spectral Feature Learning for Instrumental Variable Regressioncited by 2
  14. 2025Causal Imitation Learning under Expert-Observable and Expert-Unobservable Confoundingcited by 1
  15. 2021Approximate Last Iterate Convergence in Overparameterized GANscited by 0
  16. 2022Dual Instrumental Method for Confounded Kernelized Banditscited by 0
  17. 2025Machine learning the first stage in 2SLS: Practical guidance from bias decomposition and simulationcited by 0
  18. 2026Adaptive Estimation and Inference in Conditional Moment Models via the Discrepancy Principlecited by 0
  19. 2026Conformal Prediction for Nonparametric Instrumental Regressioncited by 0