Feedback-Based Adaptive Crossover-Rate in Evolutionary Computation

Authors: Xiaoyuan Guan, Tianyi Yang, Chunliang Zhao, Yuren Zhou

IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments and analysis show our approach effectively optimizes bi-objective problems COCZ and LOTZ in Θ(n) time during crossover, outperforming conventional crossover multi-objective evolutionary algorithms (C-MOEA) which require O(n log n) steps. For the tri-objective problem Hierarchical COCZ, our approach guarantees an expected runtime of Θ(n2 log n), while C-MOEA needs at least Ω(n2 log n) and at most O(n2 log2 n) steps. We conduct the corresponding experiments for the three problems studied to verify the theoretical analysis. The empirical results are shown in Figure 3.
Researcher Affiliation Academia School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China Key Laboratory of Machine Intelligence and Advanced Computing, MOE, Guangzhou, China School of Data and Science, Qingdao Universityof Science and Technology,Oingdao, China School of Software Engineering, Sun Yat-sen University, Zhuhai, China
Pseudocode Yes Algorithm 1 Initialization (Phase 1) and Algorithm 2 C-MOEA-MCD are provided.
Open Source Code No The paper does not provide any explicit statements about open-source code availability or links to a code repository.
Open Datasets No The paper analyzes performance on defined problems (COCZ, LOTZ, Hierarchical-COCZ) which are functions/structures, not traditional publicly available datasets with access information.
Dataset Splits No The paper discusses theoretical problems and runtime analysis, not dataset splits for training, validation, or testing.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., CPU, GPU models, memory) used for running the experiments.
Software Dependencies No The paper does not specify any software dependencies with version numbers.
Experiment Setup Yes For all the problems, denote by n the problem size, we let α = log(n 1), pr = 0.5, and we initialize the preference score list for each (dimension reduced) bi-objective string as 1n 1.