Quasi-Bayesian Dual Instrumental Variable Regression

Abstract

Recent years have witnessed an upsurge of interest in employing flexible machine learning models for instrumental variable (IV) regression, but the development of uncertainty quantification methodology is still lacking. In this work we present a novel quasi-Bayesian procedure for IV regression, building upon the recently developed kernelized IV models and the dual/minimax formulation of IV regression. We analyze the frequentist behavior of the proposed method, by establishing minimax optimal contraction rates in $L_2$ and Sobolev norms, and discussing the frequentist validity of credible balls. We further derive a scalable inference algorithm which can be extended to work with wide neural network models. Empirical evaluation shows that our method produces informative uncertainty estimates on complex high-dimensional problems.

Extended version of the NeurIPS'21 paper. ZW and YZ contribute equally

References in corpus (5)

• Rates of contraction of posterior distributions based on Gaussian process priors
• Reproducing kernel Hilbert spaces of Gaussian priors
• From $\epsilon$-entropy to KL-entropy: Analysis of minimum information complexity density estimation
• Frequentist coverage and sup-norm convergence rate in Gaussian process regression
• Analysis and Probability on Infinite-Dimensional Spaces