A. Gretton

Semiparametrically Efficient Inference for Kernel Measures of Noise Heterogeneity

Jakub Wornbard, Zikai Shen, Dimitri Meunier +1

We develop semiparametrically efficient inference for kernel measures of noise heterogeneity in additive noise models. In many applications, the regression function is estimated us…

Nonparametric Instrumental Variable Analysis Without Structural Equations: Debiased Inference on Functionals of Inverse Problems with No Solutions

Zikai Shen, Nathan Kallus, Dimitri Meunier +3

We consider debiased inference on finite-dimensional functionals of infinite-dimensional least-squares solutions to inverse problems as a way to avoid having to assume exact soluti…

Semiparametric Efficient Test for Interpretable Distributional Treatment Effects

Houssam Zenati, Arthur Gretton

Distributional treatment effects can be invisible to means: a treatment may preserve average outcomes while changing tails, modes, dispersion, or rare-event probabilities. Kernel t…

Efficient Inference after Directionally Stable Adaptive Experiments

Zikai Shen, Houssam Zenati, Nathan Kallus +3

We study inference on scalar-valued pathwise differentiable targets after adaptive data collection, such as a bandit algorithm. We introduce a novel target-specific condition, dire…

On the Hardness of Conditional Independence Testing In Practice

Zheng He, Roman Pogodin, Yazhe Li +3

Tests of conditional independence (CI) underpin a number of important problems in machine learning and statistics, from causal discovery to evaluation of predictor fairness and out…

Outcome-Aware Spectral Feature Learning for Instrumental Variable Regression

Dimitri Meunier, Jakub Wornbard, Vladimir R. Kostic +5

We address the problem of causal effect estimation in the presence of hidden confounders using nonparametric instrumental variable (IV) regression. An established approach is to us…

Nonparametric Instrumental Variable Regression with Observed Covariates

Zikai Shen, Zonghao Chen, Dimitri Meunier +3

We study the problem of nonparametric instrumental variable regression with observed covariates, which we refer to as NPIV-O. Compared with standard nonparametric instrumental vari…

Towards a Unified Analysis of Neural Networks in Nonparametric Instrumental Variable Regression: Optimization and Generalization

Zonghao Chen, Atsushi Nitanda, Arthur Gretton +1

We establish the first global convergence result of neural networks for two stage least squares (2SLS) approach in nonparametric instrumental variable regression (NPIV). This is ac…

Kernel Treatment Effects with Adaptively Collected Data

Houssam Zenati, Bariscan Bozkurt, Arthur Gretton

Adaptive experiments improve efficiency by adjusting treatment assignments based on past outcomes, but this adaptivity breaks the i.i.d.\ assumptions that underpin classical asympt…

Demystifying Spectral Feature Learning for Instrumental Variable Regression

Dimitri Meunier, Antoine Moulin, Jakub Wornbard +2

We address the problem of causal effect estimation in the presence of hidden confounders, using nonparametric instrumental variable (IV) regression. A leading strategy employs spec…

Doubly-Robust Estimation of Counterfactual Policy Mean Embeddings

Houssam Zenati, Bariscan Bozkurt, Arthur Gretton

Estimating the distribution of outcomes under counterfactual policies is critical for decision-making in domains such as recommendation, advertising, and healthcare. We propose and…

Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regression

Juno Kim, Dimitri Meunier, Arthur Gretton +2

We provide a convergence analysis of deep feature instrumental variable (DFIV) regression (Xu et al., 2021), a nonparametric approach to IV regression using data-adaptive features…

Nonparametric Instrumental Regression via Kernel Methods is Minimax Optimal

Dimitri Meunier, Zhu Li, Tim Christensen +1

We study the kernel instrumental variable (KIV) algorithm, a kernel-based two-stage least-squares method for nonparametric instrumental variable regression. We provide a convergenc…

Interventional Processes for Causal Uncertainty Quantification

Hugh Dance, Peter Orbanz, Arthur Gretton

Reliable uncertainty quantification for causal effects is crucial in high-stakes applications, but remains challenging when the target is an entire function rather than a scalar es…

Conditional Bayesian Quadrature

Zonghao Chen, Masha Naslidnyk, Arthur Gretton +1

We propose a novel approach for estimating conditional or parametric expectations in the setting where obtaining samples or evaluating integrands is costly. Through the framework o…