Large Language Models for Tuning Evolution Strategies (2405.10999v1)
Abstract: LLMs exhibit world knowledge and inference capabilities, making them powerful tools for various applications. This paper proposes a feedback loop mechanism that leverages these capabilities to tune Evolution Strategies (ES) parameters effectively. The mechanism involves a structured process of providing programming instructions, executing the corresponding code, and conducting thorough analysis. This process is specifically designed for the optimization of ES parameters. The method operates through an iterative cycle, ensuring continuous refinement of the ES parameters. First, LLMs process the instructions to generate or modify the code. The code is then executed, and the results are meticulously logged. Subsequent analysis of these results provides insights that drive further improvements. An experiment on tuning the learning rates of ES using the LLaMA3 model demonstrate the feasibility of this approach. This research illustrates how LLMs can be harnessed to improve ES algorithms' performance and suggests broader applications for similar feedback loop mechanisms in various domains.
- Evolution strategies - A comprehensive introduction. Natural Computing, 1:3–52, 2002.
- Large language model-based evolutionary optimizer: Reasoning with elitism. 2023.
- Towards learning universal hyperparameter optimizers with transformers. In Advances in Neural Information Processing Systems (NeurIPS), 2022.
- Towards optimizing with large language models. CoRR, abs/2310.05204, 2023.
- Language models as black-box optimizers for vision-language models. arXiv preprint arXiv:2309.05950, 2023.
- Using large language models for hyperparameter optimization. In NeurIPS Workshop - Foundation Models for Decision Making, 2023.
- Automl-gpt: Automatic machine learning with GPT. CoRR, abs/2305.02499, 2023.
- Can GPT-4 perform neural architecture search? CoRR, abs/2304.10970, 2023.
Collections
Sign up for free to add this paper to one or more collections.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.