Optimizing Neural Networks with Gradient Lexicase Selection

TL;DR

This paper introduces Gradient Lexicase Selection, a novel optimization method combining gradient descent and lexicase selection to improve neural network generalization across multiple image classification benchmarks.

Contribution

It presents a new framework that integrates lexicase selection into deep learning, enhancing generalization and diversity in learned representations.

Findings

Improved generalization performance on three image classification benchmarks.

Networks learn more diverse representations.

Method outperforms traditional optimization techniques.

Abstract

One potential drawback of using aggregated performance measurement in machine learning is that models may learn to accept higher errors on some training cases as compromises for lower errors on others, with the lower errors actually being instances of overfitting. This can lead to both stagnation at local optima and poor generalization. Lexicase selection is an uncompromising method developed in evolutionary computation, which selects models on the basis of sequences of individual training case errors instead of using aggregated metrics such as loss and accuracy. In this paper, we investigate how lexicase selection, in its general form, can be integrated into the context of deep learning to enhance generalization. We propose Gradient Lexicase Selection, an optimization framework that combines gradient descent and lexicase selection in an evolutionary fashion. Our experimental results demonstrate that the proposed method improves the generalization performance of various widely-used deep neural network architectures across three image classification benchmarks. Additionally, qualitative analysis suggests that our method assists networks in learning more diverse representations. Our source code is available on GitHub: https://github.com/ld-ing/gradient-lexicase.