mlsanityData to 7 Oct 2026

Spectral Representation for Causal Estimation with Hidden Confounders

arXiv 2407.10448 ↗First posted 15 Jul 2024cs.LG stat.MLcited by 12

Not on the map. Why?

Abstract (arXiv)

We address the problem of causal effect estimation where hidden confounders are present, with a focus on two settings: instrumental variable regression with additional observed confounders, and proxy causal learning. Our approach uses a singular value decomposition of a conditional expectation operator, followed by a saddle-point optimization problem, which, in the context of IV regression, can be thought of as a neural net generalization of the seminal approach due to Darolles et al. [2011]. Saddle-point formulations have gathered considerable attention recently, as they can avoid double sampling bias and are amenable to modern function approximation methods. We provide experimental validation in various settings, and show that our approach outperforms existing methods on common benchmarks.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 24 of its 53 references that are in the map. First posted on arXiv 15 Jul 2024.

Builds on

24 of 53 references.

References · 24

  1. 2019Provably Efficient Reinforcement Learning with Linear Function Approximationcited by 514
  2. 2017Causal Effect Inference with Deep Latent-Variable Modelscited by 408
  3. 2019Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Boundcited by 199
  4. 2016Identifying Causal Effects With Proxy Variables of an Unmeasured Confoundercited by 138
  5. 2019Kernel Instrumental Variable Regressioncited by 118
  6. 2019Deep Generalized Method of Moments for Instrumental Variable Analysiscited by 88
  7. 2020Minimax Estimation of Conditional Moment Modelscited by 83
  8. 2020Learning Deep Features in Instrumental Variable Regressioncited by 65
  9. 2021Proximal Causal Learning with Kernels: Two-Stage Estimation and Moment Restrictioncited by 54
  10. 2022Optimal Rates for Regularized Conditional Mean Embedding Learningcited by 50
  11. 2022Making Linear MDPs Practical via Contrastive Representation Learningcited by 49
  12. 2021Deep Proxy Causal Learning and its Application to Confounded Bandit Policy Evaluationcited by 39
12 more
  1. 2022Spectral Decomposition Representation for Reinforcement Learningcited by 35
  2. 2020Provably Efficient Neural Estimation of Structural Equation Model: An Adversarial Approachcited by 31
  3. 2015Optimal Sup-norm Rates and Uniform Inference on Nonlinear Functionals of Nonparametric IV Regressioncited by 30
  4. 2022Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learningcited by 26
  5. 2020Instrumental Variable Regression via Kernel Maximum Moment Losscited by 14
  6. 2022Latent Variable Representation for Reinforcement Learningcited by 14
  7. 2022Deep Learning Methods for Proximal Inference via Maximum Moment Restrictioncited by 13
  8. 2023Minimax Instrumental Variable Regression and L2 Convergence Guarantees without Identification or Closednesscited by 13
  9. 2022Inference on Strongly Identified Functionals of Weakly Identified Functionscited by 12
  10. 2022Spectral Representation Learning for Conditional Moment Modelscited by 12
  11. 2023Source Condition Double Robust Inference on Functionals of Inverse Problemscited by 8
  12. 2024Regularized DeepIV with Model Selectioncited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 9; 2026: 2.

12 papers.

  1. 2024Nonparametric Instrumental Regression via Kernel Methods is Minimax Optimalcited by 7
  2. 2025Self-Supervised Evolution Operator Learning for High-Dimensional Dynamical Systemscited by 7
  3. 2025Representation Learning via Non-Contrastive Mutual Informationcited by 5
  4. 2025Demystifying Spectral Feature Learning for Instrumental Variable Regressioncited by 4
  5. 2025Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regressioncited by 3
  6. 2025An Analysis of Causal Effect Estimation using Outcome Invariant Data Augmentationcited by 2
  7. 2025Outcome-Aware Spectral Feature Learning for Instrumental Variable Regressioncited by 2
  8. 2025ActiveCQ: Active Estimation of Causal Quantitiescited by 1
  9. 2025Toward Scalable and Valid Conditional Independence Testing with Spectral Representationscited by 1
  10. 2025Canonical correlation regression with noisy datacited by 0
  11. 2026Spectral Ghost in Representation Learning: from Component Analysis to Self-Supervised Learningcited by 0
  12. 2026Learning Conditional Expectation Operators via Functional Newton Updatescited by 0