Sharpness-Aware Minimization for Evolutionary Feature Construction in Regression

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Hengzhe, Chen, Qi, Xue, Bing, Banzhaf, Wolfgang, Zhang, Mengjie
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917662886461440
author Zhang, Hengzhe
Chen, Qi
Xue, Bing
Banzhaf, Wolfgang
Zhang, Mengjie
author_facet Zhang, Hengzhe
Chen, Qi
Xue, Bing
Banzhaf, Wolfgang
Zhang, Mengjie
contents In recent years, genetic programming (GP)-based evolutionary feature construction has achieved significant success. However, a primary challenge with evolutionary feature construction is its tendency to overfit the training data, resulting in poor generalization on unseen data. In this research, we draw inspiration from PAC-Bayesian theory and propose using sharpness-aware minimization in function space to discover symbolic features that exhibit robust performance within a smooth loss landscape in the semantic space. By optimizing sharpness in conjunction with cross-validation loss, as well as designing a sharpness reduction layer, the proposed method effectively mitigates the overfitting problem of GP, especially when dealing with a limited number of instances or in the presence of label noise. Experimental results on 58 real-world regression datasets show that our approach outperforms standard GP as well as six state-of-the-art complexity measurement methods for GP in controlling overfitting. Furthermore, the ensemble version of GP with sharpness-aware minimization demonstrates superior performance compared to nine fine-tuned machine learning and symbolic regression algorithms, including XGBoost and LightGBM.
format Preprint
id arxiv_https___arxiv_org_abs_2405_06869
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Sharpness-Aware Minimization for Evolutionary Feature Construction in Regression
Zhang, Hengzhe
Chen, Qi
Xue, Bing
Banzhaf, Wolfgang
Zhang, Mengjie
Machine Learning
Neural and Evolutionary Computing
In recent years, genetic programming (GP)-based evolutionary feature construction has achieved significant success. However, a primary challenge with evolutionary feature construction is its tendency to overfit the training data, resulting in poor generalization on unseen data. In this research, we draw inspiration from PAC-Bayesian theory and propose using sharpness-aware minimization in function space to discover symbolic features that exhibit robust performance within a smooth loss landscape in the semantic space. By optimizing sharpness in conjunction with cross-validation loss, as well as designing a sharpness reduction layer, the proposed method effectively mitigates the overfitting problem of GP, especially when dealing with a limited number of instances or in the presence of label noise. Experimental results on 58 real-world regression datasets show that our approach outperforms standard GP as well as six state-of-the-art complexity measurement methods for GP in controlling overfitting. Furthermore, the ensemble version of GP with sharpness-aware minimization demonstrates superior performance compared to nine fine-tuned machine learning and symbolic regression algorithms, including XGBoost and LightGBM.
title Sharpness-Aware Minimization for Evolutionary Feature Construction in Regression
topic Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2405.06869