The ART of Transfer Learning: An Adaptive and Robust Pipeline

Boxiang Wang; Yunan Wu; Chenglong Ye

doi:10.48550/arxiv.2305.00520

Back

The ART of Transfer Learning: An Adaptive and Robust Pipeline

Preprint

Open access

The ART of Transfer Learning: An Adaptive and Robust Pipeline

Boxiang Wang, Yunan Wu and Chenglong Ye

ArXiv.org

04/30/2023

DOI: 10.48550/arxiv.2305.00520

Files and links (1)

url

https://doi.org/10.48550/arXiv.2305.00520View

Preprint (Author's original)This preprint has not been evaluated by subject experts through peer review. Preprints may undergo extensive changes and/or become peer-reviewed journal articles. Open Access

Abstract

Transfer learning is an essential tool for improving the performance of primary tasks by leveraging information from auxiliary data resources. In this work, we propose Adaptive Robust Transfer Learning (ART), a flexible pipeline of performing transfer learning with generic machine learning algorithms. We establish the non-asymptotic learning theory of ART, providing a provable theoretical guarantee for achieving adaptive transfer while preventing negative transfer. Additionally, we introduce an ART-integrated-aggregating machine that produces a single final model when multiple candidate algorithms are considered. We demonstrate the promising performance of ART through extensive empirical studies on regression, classification, and sparse learning. We further present a real-data analysis for a mortality study.

Details

Title: Subtitle: The ART of Transfer Learning: An Adaptive and Robust Pipeline
Creators: Boxiang Wang
Yunan Wu
Chenglong Ye
Resource Type: Preprint
Publication Details: ArXiv.org
DOI: 10.48550/arxiv.2305.00520
ISSN: 2331-8422
Language: English
Date posted: 04/30/2023
Academic Unit: Statistics and Actuarial Science
Record Identifier: 9984400639202771

Metrics

50 Record Views