Towards a Rigorous Understanding of the Population Dynamics of the NSGA-III: Tight Runtime Bounds

2025-11-10

AI Summary

NSGA-III lacks rigorous theoretical analysis of population dynamics, particularly regarding runtime behavior on canonical multi-objective problems. Method: We conduct the first tight runtime analysis of NSGA-III on the bi-objective OneMinMax benchmark, combining probabilistic analysis with modeling of selection pressure to rigorously characterize how reference-point guidance and crowding-distance assignment shape population distribution. Contribution/Results: We establish a tight bound on its expected number of generations: Ω(n² log n / μ) for the lower bound and O(n log n) for the upper bound—achieving tightness. Moreover, we prove that NSGA-III outperforms NSGA-II by a factor of μ/n in expected runtime, thereby filling a fundamental theoretical gap for this algorithm on classical multi-objective optimization problems. This work provides the first rigorous runtime guarantee for NSGA-III’s convergence and diversity maintenance, advancing the theoretical understanding of reference-point-based evolutionary multi-objective optimization.

Technology Category

• Search and Optimization: Evolutionary Computation
• Constraint Satisfaction and Optimization: Other Foundations of Constraint Satisfaction
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Web Mining and Content Analysis: Models for Web evolution

Abstract

Evolutionary algorithms are widely used for solving multi-objective optimization problems. A prominent example is NSGA-III, which is particularly well suited for solving problems involving more than three objectives, distinguishing it from the classical NSGA-II. Despite its empirical success, the theoretical understanding of NSGA III remains very limited, especially with respect to runtime analysis. A central open problem concerns its population dynamics, which involve controlling the maximum number of individuals sharing the same fitness value during the exploration process. In this paper, we make a significant step towards such an understanding by proving tight runtime bounds for NSGA-III on the bi-objective OneMinMax ($2$-OMM) problem. Firstly, we prove that NSGA-III requires $Omega(n^2 log(n) / mu)$ generations in expectation to optimize $2$-OMM assuming the population size $mu$ satisfies $n+1 leq mu =O(log(n)^c(n+1))$ where $n$ denotes the problem size and $c<1$ is a constant. Apart from~cite{opris2025multimodal}, this is the first proven lower runtime bound for NSGA-III on a classical benchmark problem. Complementing this, we secondly improve the best known upper bound of NSGA-III on the $m$-objective OneMinMax problem ($m$-OMM) of $O(n log(n))$ generations by a factor of $mu /(2n/m + 1)^{m/2}$ for a constant number $m$ of objectives and population size $(2n/m + 1)^{m/2} leq mu in O(sqrt{log(n)} (2n/m + 1)^{m/2})$. This yields tight runtime bounds in the case $m = 2$, and the surprising result that NSGA-III beats NSGA-II by a factor of $mu/n$ in the expected runtime.

Problem

• Theoretical understanding of NSGA-III population dynamics remains limited
• Proving tight runtime bounds for NSGA-III on multi-objective problems
• Analyzing population size impact on NSGA-III optimization performance

Innovation

• Proving tight runtime bounds for NSGA-III
• Analyzing population dynamics on multi-objective problems
• Improving upper bounds for OneMinMax optimization