EconBase
← All papers

Fast Instrument Learning with Faster Rates

Ziyu Wang, Yuhao Zhou, Jun Zhu

arXiv 22 May 2022 · Statistics — Machine Learning

arXiv:2205.10772 · PDF · DOI · OpenAlex · Extracted main text

Abstract

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.

Citation extraction

93
references
317
in-text mentions
93
distinct cited
0
self-citations
8,242
main-text words

appendix boundary found by appendix_command · 24% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1R. Zhang, M. Imaizumi, B. Schölkopf, and K. Muandet, “Maximum moment… (2020) Maximum moment restriction for instrumental variable regression0.9416483%
2K. Muandet, A. Mehrjou, S. K. Lee, and A. Raj, “Dual instrumental va… (2020) Dual instrumental variable regression0.8947571%
3R. Singh, M. Sahani, and A. Gretton, “enKernel Instrumental variable… (2019) enKernel Instrumental variable regression0.87412667%
4K. Kato, “enQuasi-Bayesian analysis of nonparametric instrumental va… (2013) enQuasi-Bayesian analysis of nonparametric instrumental variables models0.8434375%
5A. Bennett, N. Kallus, and T. Schnabel, “Deep generalized method of… (2019) Deep generalized method of moments for instrumental variable analysis0.84310460%
6B. Ghorbani, S. Mei, T. Misiakiewicz, and A. Montanari, “Limitations… (2019) Limitations of lazy training of two-layers neural networks0.84333100%
7C. Wei, J. D. Lee, Q. Liu, and T. Ma, “Regularization matters: Gener… (2019) Regularization matters: Generalization and optimization of neural nets v.s. their induced kernel0.84333100%
8N. Dikkala, G. Lewis, L. Mackey, and V. Syrgkanis, “Minimax estimati… (2020) Minimax estimation of conditional moment models0.82532856%
9J. Hartford, G. Lewis, K. Leyton-Brown, and M. Taddy, “Deep IV: A fl… (2017) Deep IV: A flexible approach for counterfactual prediction0.79410550%
10J. Schmidt-Hieber, “Nonparametric regression using deep neural netwo… (2020) Nonparametric regression using deep neural networks with ReLU activation function0.77313546%

Showing the top 10 of 93 scored citations.