English

Fast and Efficient Local Search for Genetic Programming Based Loss Function Learning

Neural and Evolutionary Computing 2024-03-05 v1 Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning

Abstract

In this paper, we develop upon the topic of loss function learning, an emergent meta-learning paradigm that aims to learn loss functions that significantly improve the performance of the models trained under them. Specifically, we propose a new meta-learning framework for task and model-agnostic loss function learning via a hybrid search approach. The framework first uses genetic programming to find a set of symbolic loss functions. Second, the set of learned loss functions is subsequently parameterized and optimized via unrolled differentiation. The versatility and performance of the proposed framework are empirically validated on a diverse set of supervised learning tasks. Results show that the learned loss functions bring improved convergence, sample efficiency, and inference performance on tabulated, computer vision, and natural language processing problems, using a variety of task-specific neural network architectures.

Keywords

Cite

@article{arxiv.2403.00865,
  title  = {Fast and Efficient Local Search for Genetic Programming Based Loss Function Learning},
  author = {Christian Raymond and Qi Chen and Bing Xue and Mengjie Zhang},
  journal= {arXiv preprint arXiv:2403.00865},
  year   = {2024}
}

Comments

arXiv admin note: substantial text overlap with arXiv:2209.08907