From interpretability to inference: an estimation framework for universal approximators
This provides a method for interpretable inference in machine learning models, applicable to tasks like heterogeneous treatment effect estimation.
The authors tackled the problem of estimation and inference for universal approximators by decomposing model predictions into Shapley values, showing that this estimation is asymptotically unbiased and introducing Shapley regressions to uncover the true data generating process from noisy data.
We present a novel framework for estimation and inference with the broad class of universal approximators. Estimation is based on the decomposition of model predictions into Shapley values. Inference relies on analyzing the bias and variance properties of individual Shapley components. We show that Shapley value estimation is asymptotically unbiased, and we introduce Shapley regressions as a tool to uncover the true data generating process from noisy data alone. The well-known case of the linear regression is the special case in our framework if the model is linear in parameters. We present theoretical, numerical, and empirical results for the estimation of heterogeneous treatment effects as our guiding example.