Eliminating Meta Optimization Through Selfreferential Meta Learning

# Eliminating Meta Optimization Through Self-Referential Meta Learning

**arXiv ID:** 2212.14392
**Authors:** Louis Kirsch, Jürgen Schmidhuber
**Published:** 2022-12-29T17:53:40Z
**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.

## Skill Description

This skill is generated from the arXiv paper: Eliminating Meta Optimization Through Self-Referential Meta Learning (2212.14392).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2212.14392](http://arxiv.org/abs/2212.14392v1)