mlsanityData to 7 Oct 2026

Fast Instrument Learning with Faster Rates

arXiv 2205.10772 ↗First posted 22 May 2022stat.ML cs.LG econ.EMcited by 6

Not on the map. Why?

Abstract (arXiv)

We investigate nonlinear instrumental variable (IV) regression given high-dimensional instruments. We propose a simple algorithm which combines kernelized IV methods and an arbitrary, adaptive regression algorithm, accessed as a black box. Our algorithm enjoys faster-rate convergence and adapts to the dimensionality of informative latent features, while avoiding an expensive minimax optimization procedure, which has been necessary to establish similar guarantees. It further brings the benefit of flexible machine learning models to quasi-Bayesian uncertainty quantification, likelihood-based model selection, and model averaging. Simulation studies demonstrate the competitive performance of our method.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 26 of its 102 references that are in the map. First posted on arXiv 22 May 2022.

Builds on

26 of 102 references.

References · 26

  1. 2017Nonparametric regression using deep neural networks with ReLU activation functioncited by 431
  2. 2014In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learningcited by 339
  3. 2014Breaking the Curse of Dimensionality with Convex Neural Networkscited by 329
  4. 2021User-friendly introduction to PAC-Bayes boundscited by 234
  5. 2020Few-Shot Learning via Learning the Representation, Provablycited by 213
  6. 2018Gaussian Processes and Kernel Methods: A Review on Connections and Equivalencescited by 188
  7. 2020On the Theory of Transfer Learning: The Importance of Task Diversitycited by 186
  8. 2016Generalization Properties of Learning with Random Featurescited by 163
  9. 2019Orthogonal Statistical Learningcited by 150
  10. 2018Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernelcited by 131
  11. 2019Kernel Instrumental Variable Regressioncited by 118
  12. 2017Sobolev Norm Learning Rates for Regularized Least-Squares Algorithmcited by 113
14 more
  1. 2015Less is More: Nystr"om Computational Regularizationcited by 89
  2. 2019Deep Generalized Method of Moments for Instrumental Variable Analysiscited by 88
  3. 2019Limitations of Lazy Training of Two-layers Neural Networkscited by 87
  4. 2020Minimax Estimation of Conditional Moment Modelscited by 83
  5. 2020Learning Deep Features in Instrumental Variable Regressioncited by 65
  6. 2020Provably Efficient Neural Estimation of Structural Equation Model: An Adversarial Approachcited by 31
  7. 2015Optimal Sup-norm Rates and Uniform Inference on Nonlinear Functionals of Nonparametric IV Regressioncited by 30
  8. 2019Machine Learning Estimation of Heterogeneous Treatment Effects with Instrumentscited by 29
  9. 2020Estimation and Inference with Trees and Forests in High Dimensionscited by 14
  10. 2013Regularization Methods for High-Dimensional Instrumental Variables Regression With an Application to Genetical Genomicscited by 9
  11. 2019Bayesian Deconditional Kernel Mean Embeddingscited by 6
  12. 2020Mostly Harmless Machine Learning: Learning Optimal Instruments in Linear IV Modelscited by 4
  13. 2021Quasi-Bayesian Dual Instrumental Variable Regressioncited by 3
  14. 2021Instrument Space Selection for Kernel Maximum Moment Restrictioncited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 0; 2024: 1; 2025: 3; 2026: 1.

6 papers.

  1. 2022Spectral Representation Learning for Conditional Moment Modelscited by 12
  2. 2025Koopman-Equivariant Gaussian Processescited by 6
  3. 2025Demystifying Spectral Feature Learning for Instrumental Variable Regressioncited by 4
  4. 2024On Uncertainty Quantification for Near-Bayes Optimal Algorithmscited by 3
  5. 2025Outcome-Aware Spectral Feature Learning for Instrumental Variable Regressioncited by 2
  6. 2026BGM-IV: AI-Powered Bayesian Generative Modeling for Instrumental Variable Regression with High-Dimensional Covariatescited by 0