Early-stopped aggregation: Adaptive inference with computational efficiency

TL;DR

This paper introduces early-stopped aggregation (ESA), a computationally efficient framework for adaptive model aggregation that reduces unnecessary calculations by early stopping, applicable to Bayesian and frequentist methods.

Contribution

The paper proposes a novel early-stopping based aggregation framework that unifies Bayesian and frequentist approaches, achieving optimal adaptive rates with improved computational efficiency.

Findings

ESA achieves optimal adaptive contraction rates in variational Bayes.

ESA extends to variational empirical Bayes with data-dependent hyperparameters.

ESA demonstrates strong empirical performance and efficiency in numerical studies.

Abstract

When considering a model selection or, more generally, an aggregation approach for adaptive statistical inference, it is often necessary to compute estimators over a wide range of model complexities including unnecessarily large models even when the true data-generating process is relatively simple, due to the lack of prior knowledge. This requirement can lead to substantial computational inefficiency. In this work, we propose a novel framework for efficient model aggregation called the early-stopped aggregation (ESA): instead of computing and aggregating estimators for all candidate models, we compute only a small number of simpler ones using an early-stopping criterion and aggregate only these for final inference. Our framework is versatile and applies to both Bayesian model selection, in particular, within the variational Bayes framework, and frequentist estimation, including a general penalized estimation setting. We investigate adaptive optimal property of the ESA approach across three learning paradigms. We first show that ESA achieves optimal adaptive contraction rates in the variational Bayes setting under mild conditions. We extend this result to variational empirical Bayes, where prior hyperparameters are chosen in a data-dependent manner. In addition, we apply the ESA approach to frequentist aggregation including both penalization-based and sample-splitting implementations, and establish corresponding theory. As we demonstrate, there is a clear unification between early-stopped Bayes and frequentist penalized aggregation, with a common "energy" functional comprising a data-fitting term and a complexity-control term that drives both procedures. We further present several applications and numerical studies that highlight the efficiency and strong performance of the proposed approach.