English

Eliminating Meta Optimization Through Self-Referential Meta Learning

Machine Learning 2023-01-02 v1 Artificial Intelligence Neural and Evolutionary Computing Machine Learning

Abstract

Meta Learning automates the search for learning algorithms. At the same time, it creates a dependency on human engineering on the meta-level, where meta learning algorithms need to be designed. In this paper, we investigate self-referential meta learning systems that modify themselves without the need for explicit meta optimization. We discuss the relationship of such systems to in-context and memory-based meta learning and show that self-referential neural networks require functionality to be reused in the form of parameter sharing. Finally, we propose fitness monotonic execution (FME), a simple approach to avoid explicit meta optimization. A neural network self-modifies to solve bandit and classic control tasks, improves its self-modifications, and learns how to learn, purely by assigning more computational resources to better performing solutions.

Keywords

Cite

@article{arxiv.2212.14392,
  title  = {Eliminating Meta Optimization Through Self-Referential Meta Learning},
  author = {Louis Kirsch and Jürgen Schmidhuber},
  journal= {arXiv preprint arXiv:2212.14392},
  year   = {2023}
}

Comments

The first version appeared at ICML 2022, DARL Workshop

R2 v1 2026-06-28T07:56:14.080Z