Early stopping criteria to counteract overfitting in genetic programming

Authors:
Clíodhna Tuite;Alexandros Agapitos;Michael O'Neill;Anthony Brabazon
Affiliations:
University College Dublin, Dublin, Ireland;University College Dublin, Dublin, Ireland;University College Dublin, Dublin, Ireland;University College Dublin, Dublin, Ireland
Venue:
Proceedings of the 13th annual conference companion on Genetic and evolutionary computation
Year:
2011

Citing 6
Cited 2

No free lunch for early stopping

Neural Computation
Machine Learning

Machine Learning
Grammatical Evolution: Evolutionary Automatic Programming in an Arbitrary Language

Grammatical Evolution: Evolutionary Automatic Programming in an Arbitrary Language
GEVA: grammatical evolution in Java

ACM SIGEVOlution
A preliminary investigation of overfitting in evolutionary driven model induction: implications for financial modelling

EvoApplications'11 Proceedings of the 2011 international conference on Applications of evolutionary computation - Volume Part II
Pricing and hedging derivative securities with neural networks: Bayesian regularization, early stopping, and bagging

IEEE Transactions on Neural Networks

Where should we stop? an investigation on early stopping for GP learning

SEAL'12 Proceedings of the 9th international conference on Simulated Evolution and Learning
Adaptive distance metrics for nearest neighbour classification based on genetic programming

EuroGP'13 Proceedings of the 16th European conference on Genetic Programming

Quantified Score

Hi-index	0.00

Visualization

Abstract

Early stopping typically stops training the first time validation fitness disimproves. This may not be the best strategy given that validation fitness can subsequently increase or decrease. We examine the effects of stopping subsequent to the first disimprovement in validation fitness, on symbolic regression problems. Stopping points are determined using criteria which measure generalisation loss and training progress. Results suggest that these criteria can improve the generalistion ability of symbolic regression functions evolved using Grammar-based GP.