Estimation of Over-parameterized Models from an Auto-Modeling Perspective

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Jiang, Yiran, Liu, Chuanhai
Natura: Preprint
Pubblicazione: 2022
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917859062448128
author Jiang, Yiran
Liu, Chuanhai
author_facet Jiang, Yiran
Liu, Chuanhai
contents From a model-building perspective, we propose a paradigm shift for fitting over-parameterized models. Philosophically, the mindset is to fit models to future observations rather than to the observed sample. Technically, given an imputation method to generate future observations, we fit over-parameterized models to these future observations by optimizing an approximation of the desired expected loss function based on its sample counterpart and an adaptive $\textit{duality function}$. The required imputation method is also developed using the same estimation technique with an adaptive $m$-out-of-$n$ bootstrap approach. We illustrate its applications with the many-normal-means problem, $n < p$ linear regression, and neural network-based image classification of MNIST digits. The numerical results demonstrate its superior performance across these diverse applications. While primarily expository, the paper conducts an in-depth investigation into the theoretical aspects of the topic. It concludes with remarks on some open problems.
format Preprint
id arxiv_https___arxiv_org_abs_2206_01824
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Estimation of Over-parameterized Models from an Auto-Modeling Perspective
Jiang, Yiran
Liu, Chuanhai
Methodology
Statistics Theory
Applications
From a model-building perspective, we propose a paradigm shift for fitting over-parameterized models. Philosophically, the mindset is to fit models to future observations rather than to the observed sample. Technically, given an imputation method to generate future observations, we fit over-parameterized models to these future observations by optimizing an approximation of the desired expected loss function based on its sample counterpart and an adaptive $\textit{duality function}$. The required imputation method is also developed using the same estimation technique with an adaptive $m$-out-of-$n$ bootstrap approach. We illustrate its applications with the many-normal-means problem, $n < p$ linear regression, and neural network-based image classification of MNIST digits. The numerical results demonstrate its superior performance across these diverse applications. While primarily expository, the paper conducts an in-depth investigation into the theoretical aspects of the topic. It concludes with remarks on some open problems.
title Estimation of Over-parameterized Models from an Auto-Modeling Perspective
topic Methodology
Statistics Theory
Applications
url https://arxiv.org/abs/2206.01824