A Unified Framework for Semiparametrically Efficient Semi-Supervised Learning

TL;DR

This paper develops a unified semiparametric efficiency framework for semi-supervised learning, proposing estimators that leverage unlabeled data to improve inference, with theoretical guarantees and applications to various statistical problems.

Contribution

It introduces a general efficiency theory for semi-supervised inference, proposing safe and efficient estimators that incorporate unlabeled data and machine learning predictions.

Findings

The safe estimator is at least as efficient as supervised methods.

The efficient estimator achieves the semiparametric efficiency bound.

Simulations demonstrate improved performance of the proposed estimators.

Abstract

We consider statistical inference under a semi-supervised setting where we have access to both a labeled dataset consisting of pairs $\{X_i, Y_i \}_{i=1}^n$ and an unlabeled dataset $\{ X_i \}_{i=n+1}^{n+N}$. We ask the question: under what circumstances, and by how much, can incorporating the unlabeled dataset improve upon inference using the labeled data? To answer this question, we investigate semi-supervised learning through the lens of semiparametric efficiency theory. We characterize the efficiency lower bound under the semi-supervised setting for an arbitrary inferential problem, and show that incorporating unlabeled data can potentially improve efficiency if the parameter is not well-specified. We then propose two types of semi-supervised estimators: a safe estimator that imposes minimal assumptions, is simple to compute, and is guaranteed to be at least as efficient as the initial supervised estimator; and an efficient estimator, which -- under stronger assumptions -- achieves the semiparametric efficiency bound. Our findings unify existing semiparametric efficiency results for particular special cases, and extend these results to a much more general class of problems. Moreover, we show that our estimators can flexibly incorporate predicted outcomes arising from ``black-box" machine learning models, and thereby achieve the same goal as prediction-powered inference (PPI), but with superior theoretical guarantees. We also provide a complete understanding of the theoretical basis for the existing set of PPI methods. Finally, we apply the theoretical framework developed to derive and analyze efficient semi-supervised estimators in a number of settings, including M-estimation, U-statistics, and average treatment effect estimation, and demonstrate the performance of the proposed estimators via simulations.