First Steps Towards a Runtime Analysis of Neuroevolution

DOI10.1145/3594805.3607125arXiv2307.00799MaRDI QIDQ6120967

Paul Fischer, Carsten Witt, Unnamed Author

Publication date: 23 February 2024

Published in: Proceedings of the 17th ACM/SIGEVO Conference on Foundations of Genetic Algorithms (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2307.00799

zbMATH Keywords

theory; runtime analysis; neuroevolution

Mathematics Subject Classification ID

68W50: Evolutionary algorithms, genetic algorithms (computational aspects)

90C59: Approximation methods and heuristics in mathematical programming

68T20: Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.)

Cites Work

• Bioinspired computation in combinatorial optimization. Algorithms and their computational complexity
• Analyzing evolutionary algorithms. The computer science perspective.
• Precision, local search and unimodal functions
• On the analysis of the \((1+1)\) evolutionary algorithm
• Static and self-adjusting mutation strengths for multi-valued decision variables
• Multiplicative drift analysis
• Self-adjusting mutation rates with provably optimal success rules
• First-hitting times under drift
• Algorithmic analysis of a basic evolutionary algorithm for continuous optimization
• (1+1) EA on Generalized Dynamic OneMax
• Training a Single Sigmoidal Neuron Is Hard
• Theory of Evolutionary Computation
• Automata, Languages and Programming
• Unnamed Item
• Unnamed Item
• Unnamed Item