Runtime Analysis of the SMS-EMOA for Many-Objective Optimization

Authors: Weijie Zheng, Benjamin Doerr

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

Reproducibility Variable Result LLM Response
Research Type Theoretical This paper conducts the first rigorous runtime analysis of the SMS-EMOA for many-objective optimization. To this aim, we first propose a many-objective counterpart, the m-objective m OJZJ problem, of the bi-objective OJZJ benchmark, which is the first many-objective multimodal benchmark used in a mathematical runtime analysis. We prove that SMS-EMOA computes the full Pareto front of this benchmark in an expected number of O(M 2nk) iterations
Researcher Affiliation Academia 1 School of Computer Science and Technology, International Research Institute for Artificial Intelligence, Harbin Institute of Technology, Shenzhen, China 2 Laboratoire d Informatique (LIX), Ecole Polytechnique, CNRS, Institut Polytechnique de Paris, Palaiseau, France
Pseudocode Yes Algorithm 1: SMS-EMOA
Open Source Code No The paper does not provide an explicit statement or link to open-source code for the methodology described in this paper.
Open Datasets No The paper defines and analyzes theoretical benchmarks (e.g., m OJZJ, ONEMINMAX, LOTZ) rather than using empirical datasets. These benchmarks are mathematical problem definitions, not publicly available data in the traditional sense.
Dataset Splits No As a theoretical runtime analysis paper, it does not involve empirical experiments with training, validation, or test data splits.
Hardware Specification No As a theoretical runtime analysis paper, it does not describe specific hardware used for running experiments.
Software Dependencies No As a theoretical runtime analysis paper, it does not specify software dependencies with version numbers for experimental reproducibility.
Experiment Setup No As a theoretical runtime analysis paper, it does not describe an experimental setup with hyperparameters or system-level training settings.