Provable Speedups From Dynamic Population Sizes in Evolutionary Algorithms for Multiobjective Optimization

• URL: http://arxiv.org/abs/2607.23800v1
• Date: Sun, 26 Jul 2026 19:03:29 GMT
• Title: Provable Speedups From Dynamic Population Sizes in Evolutionary Algorithms for Multiobjective Optimization
• Abstract summary: We introduce the bi-objective problem class CLIMB and analyze the runtime of GSEMO and the widely used NSGA-II.<n>Our results show that allowing a dynamic population size for NSGA-II can lead to a moderate improvement, yielding a speedup of order $(sqrtn/log n)$.<n>This is the first rigorous runtime analysis in multi-objective optimization demonstrating a super-constant speedup of GSEMO over NSGA-II.
• Score: 5.482532589225553
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: This paper investigates the role of dynamic population sizes in evolutionary multi-objective optimization. Although such approaches are widely used in practice, their benefits remain poorly understood, and rigorous runtime analyses explaining when and why they help are still scarce. To address this, we introduce the bi-objective problem class CLIMB and analyze the runtime of GSEMO and the widely used NSGA-II on this problem. Our results show that allowing a dynamic population size for NSGA-II can lead to a moderate improvement, yielding a speedup of order $Ω(\sqrt{n}/\log n)$. In particular, we prove that GSEMO and NSGA-II-DYN, a version of NSGA-II with dynamic population sizes we propose in this paper, can find the Pareto front of CLIMB in expected $O(n \log n)$ fitness evaluations, whereas NSGA-II with a fixed population size requires $Ω(n^{1.5})$ fitness evaluations in expectation. To the best of our knowledge, this is the first rigorous runtime analysis in multi-objective optimization demonstrating a super-constant speedup of GSEMO over NSGA-II. Our analysis builds on concepts from single-objective optimization, like the evolution of population diversity over time, and employs the well-known family-three method to prove the lower bound.

Related papers

• Bidirectional Looking with A Novel Double Exponential Moving Average to Adaptive and Non-adaptive Momentum Optimizers [109.52244418498974]
  We propose a novel textscAdmeta (textbfADouble exponential textbfMov averagtextbfE textbfAdaptive and non-adaptive momentum) framework. We provide two implementations, textscAdmetaR and textscAdmetaS, the former based on RAdam and the latter based on SGDM.
  arXiv  Detail & Related papers  (2023-07-02T18:16:06Z)
• Quantifying the Optimization and Generalization Advantages of Graph Neural Networks Over Multilayer Perceptrons [50.33260238739837]
  Graph networks (GNNs) have demonstrated remarkable capabilities in learning from graph-structured data.<n>There remains a lack of analysis comparing GNNs and generalizations from an optimization and generalization perspective.
  arXiv  Detail & Related papers  (2023-06-24T10:21:11Z)
• Analysing the Robustness of NSGA-II under Noise [1.7205106391379026]
  First runtime analyses of the famous and highly cited EMO algorithm NSGA-II have emerged. It is unclear how and when NSGA-II can outperform GSEMO.
  arXiv  Detail & Related papers  (2023-06-07T15:33:54Z)
• A Mathematical Runtime Analysis of the Non-dominated Sorting Genetic Algorithm III (NSGA-III) [9.853329403413701]
  The Non-dominated Sorting Genetic Algorithm II (NSGA-II) is the most prominent multi-objective evolutionary algorithm for real-world applications. We provide the first mathematical runtime analysis of the NSGA-III, a refinement of the NSGA-II aimed at better handling more than two objectives.
  arXiv  Detail & Related papers  (2022-11-15T15:10:36Z)
• NAG-GS: Semi-Implicit, Accelerated and Robust Stochastic Optimizer [45.47667026025716]
  We propose a novel, robust and accelerated iteration that relies on two key elements. The convergence and stability of the obtained method, referred to as NAG-GS, are first studied extensively. We show that NAG-arity is competitive with state-the-art methods such as momentum SGD with weight decay and AdamW for the training of machine learning models.
  arXiv  Detail & Related papers  (2022-09-29T16:54:53Z)
• From Understanding the Population Dynamics of the NSGA-II to the First Proven Lower Bounds [10.107150356618588]
  We prove that the NSGA-II with suitable population size needs $Omega(Nnlog n)$ function evaluations. For the computation of the crowding distance contributions of the two objectives, we even obtain a runtime estimate that is tight including the leading constant.
  arXiv  Detail & Related papers  (2022-09-28T10:11:20Z)
• Stability and Generalization Analysis of Gradient Methods for Shallow Neural Networks [59.142826407441106]
  We study the generalization behavior of shallow neural networks (SNNs) by leveraging the concept of algorithmic stability. We consider gradient descent (GD) and gradient descent (SGD) to train SNNs, for both of which we develop consistent excess bounds.
  arXiv  Detail & Related papers  (2022-09-19T18:48:00Z)
• A First Runtime Analysis of the NSGA-II on a Multimodal Problem [17.049516028133958]
  This work shows that the NSGA-II copes with the local optima of the OneJumpZeroJump problem at least as well as the global SEMO algorithm. Overall, this work shows that the NSGA-II copes with the local optima of the OneJumpZeroJump problem at least as well as the global SEMO algorithm.
  arXiv  Detail & Related papers  (2022-04-28T19:44:47Z)
• Improved Convergence Rate of Stochastic Gradient Langevin Dynamics with Variance Reduction and its Application to Optimization [50.83356836818667]
  gradient Langevin Dynamics is one of the most fundamental algorithms to solve non-eps optimization problems. In this paper, we show two variants of this kind, namely the Variance Reduced Langevin Dynamics and the Recursive Gradient Langevin Dynamics.
  arXiv  Detail & Related papers  (2022-03-30T11:39:00Z)
• Mathematical Runtime Analysis for the Non-Dominated Sorting Genetic Algorithm II (NSGA-II) [16.904475483445452]
  We show that runtime analyses are feasible also for the NSGA-II. We prove that with a population size four times larger than the size of the Pareto front, the NSGA-II satisfies the same runtime guarantees as the SEMO and GSEMO algorithms.
  arXiv  Detail & Related papers  (2021-12-16T03:00:20Z)
• Result Diversification by Multi-objective Evolutionary Algorithms with Theoretical Guarantees [94.72461292387146]
  We propose to reformulate the result diversification problem as a bi-objective search problem, and solve it by a multi-objective evolutionary algorithm (EA) We theoretically prove that the GSEMO can achieve the optimal-time approximation ratio, $1/2$. When the objective function changes dynamically, the GSEMO can maintain this approximation ratio in running time, addressing the open question proposed by Borodin et al.
  arXiv  Detail & Related papers  (2021-10-18T14:00:22Z)
• Interpreting and Unifying Graph Neural Networks with An Optimization Framework [47.44773358082203]
  Graph Neural Networks (GNNs) have received considerable attention on graph-structured data learning. In this paper, we establish a surprising connection between different propagation mechanisms with a unified optimization problem. Our proposed unified optimization framework, summarizing the commonalities between several of the most representative GNNs, opens up new opportunities for flexibly designing new GNNs.
  arXiv  Detail & Related papers  (2021-01-28T08:06:02Z)
• Binarized Graph Neural Network [65.20589262811677]
  We develop a binarized graph neural network to learn the binary representations of the nodes with binary network parameters. Our proposed method can be seamlessly integrated into the existing GNN-based embedding approaches. Experiments indicate that the proposed binarized graph neural network, namely BGN, is orders of magnitude more efficient in terms of both time and space.
  arXiv  Detail & Related papers  (2020-04-19T09:43:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.