English
Related papers

Related papers: Tight Runtime Bounds for Static Unary Unbiased Evo…

200 papers

We study the $(1,\lambda)$-EA with mutation rate $c/n$ for $c\le 1$, where the population size is adaptively controlled with the $(1:s+1)$-success rule. Recently, Hevia Fajardo and Sudholt have shown that this setup with $c=1$ is efficient…

Neural and Evolutionary Computing · Computer Science 2023-07-13 Marc Kaufmann , Maxime Larcher , Johannes Lengler , Xun Zou

The $(1+(\lambda,\lambda))$ genetic algorithm, first proposed at GECCO 2013, showed a surprisingly good performance on so me optimization problems. The theoretical analysis so far was restricted to the OneMax test function, where this GA…

Neural and Evolutionary Computing · Computer Science 2017-04-17 Maxim Buzdalov , Benjamin Doerr

Self-adjustment of parameters can significantly improve the performance of evolutionary algorithms. A notable example is the $(1+(\lambda,\lambda))$ genetic algorithm, where the adaptation of the population size helps to achieve the linear…

Neural and Evolutionary Computing · Computer Science 2019-04-17 Anton Bassin , Maxim Buzdalov

Recently a mechanism called stagnation detection was proposed that automatically adjusts the mutation rate of evolutionary algorithms when they encounter local optima. The so-called $SD-(1+1)EA$ introduced by Rajabi and Witt (GECCO 2020)…

Neural and Evolutionary Computing · Computer Science 2021-04-19 Amirhossein Rajabi , Carsten Witt

We study evolutionary algorithms in a dynamic setting, where for each generation a different fitness function is chosen, and selection is performed with respect to the current fitness function. Specifically, we consider Dynamic BinVal, in…

Neural and Evolutionary Computing · Computer Science 2021-07-09 Johannes Lengler , Simone Riedi

We study how Reinforcement Learning can be employed to optimally control parameters in evolutionary algorithms. We control the mutation probability of a (1+1) evolutionary algorithm on the OneMax function. This problem is modeled as a…

Neural and Evolutionary Computing · Computer Science 2019-05-10 Luca Mossina , Emmanuel Rachelson , Daniel Delahaye

Combinatorial optimization problems are a prominent application area of evolutionary algorithms, where the (1+1) EA is one of the most investigated. We extend this algorithm by introducing some problem knowledge with a specialized mutation…

Combinatorics · Mathematics 2022-03-17 Samuel Baguley , Tobias Friedrich , Timo Kötzing , Xiaoyue Li , Marcus Pappik , Ziena Zeif

We establish global convergence of the (1+1) evolution strategy, i.e., convergence to a critical point independent of the initial state. More precisely, we show the existence of a critical limit point, using a suitable extension of the…

Neural and Evolutionary Computing · Computer Science 2020-11-20 Tobias Glasmachers

Following a line of work that takes advantage of vast machine-learned data to enhance online algorithms with (possibly erroneous) information about future inputs, we consider predictions in the context of deterministic algorithms for the…

Data Structures and Algorithms · Computer Science 2025-02-17 Christodoulos Karavasilis

While the theoretical analysis of evolutionary algorithms (EAs) has made significant progress for pseudo-Boolean optimization problems in the last 25 years, only sporadic theoretical results exist on how EAs solve permutation-based…

Neural and Evolutionary Computing · Computer Science 2022-10-07 Benjamin Doerr , Yassine Ghannane , Marouane Ibn Brahim

Evolutionary algorithms (EAs) have found many successful real-world applications, where the optimization problems are often subject to a wide range of uncertainties. To understand the practical behaviors of EAs theoretically, there are a…

Computational Complexity · Computer Science 2022-12-07 Chao Bian , Chao Qian , Ke Tang , Yang Yu

For every mutation rate $p \in (0, 1)$, and for all $\varepsilon > 0$, there is a fitness function $f : \{0,1\}^n \to \mathbb{R}$ with a unique maximum for which the optimal mutation rate for the $(1+1)$ evolutionary algorithm on $f$ is in…

Neural and Evolutionary Computing · Computer Science 2026-05-12 Andrew James Kelley

We perform a rigorous runtime analysis for the Univariate Marginal Distribution Algorithm on the LeadingOnes function, a well-known benchmark function in the theory community of evolutionary computation with a high correlation between…

Neural and Evolutionary Computing · Computer Science 2019-04-22 Per Kristian Lehre , Phan Trung Hai Nguyen

While the theoretical analysis of evolutionary algorithms (EAs) has made significant progress for pseudo-Boolean optimization problems in the last 25 years, only sporadic theoretical results exist on how EAs solve permutation-based…

Neural and Evolutionary Computing · Computer Science 2024-04-23 Benjamin Doerr , Yassine Ghannane , Marouane Ibn Brahim

Evolutionary neural architecture search (ENAS) employs evolutionary algorithms to find high-performing neural architectures automatically, and has achieved great success. However, compared to the empirical success, its rigorous theoretical…

Neural and Evolutionary Computing · Computer Science 2024-04-09 Zeqiong Lv , Chao Qian , Yanan Sun

The heavy-tailed mutation operator, proposed by Doerr, Le, Makhmara, and Nguyen (2017) for evolutionary algorithms, is based on the power-law assumption of mutation rate distribution. Here we generalize the power-law assumption using a…

Neural and Evolutionary Computing · Computer Science 2026-04-02 Anton V. Eremeev , Dmitri V. Silaev , Valentin A. Topchii

When a problem instance is perturbed by a small modification, one would hope to find a good solution for the new instance by building on a known good solution for the previous one. Via a rigorous mathematical analysis, we show that…

Neural and Evolutionary Computing · Computer Science 2019-04-17 Benjamin Doerr , Carola Doerr , Frank Neumann

The $(1+(\lambda,\lambda))$ genetic algorithm is a recently proposed single-objective evolutionary algorithm with several interesting properties. We show that its main working principle, mutation with a high rate and crossover as repair…

Neural and Evolutionary Computing · Computer Science 2022-10-10 Benjamin Doerr , Omar El Hadri , Adrien Pinard

In this article we present an Elitism Levels Traverse Mechanism that we designed to find bounds on population-based Evolutionary algorithms solving unimodal functions. We prove its efficiency theoretically and test it on OneMax function…

Neural and Evolutionary Computing · Computer Science 2012-04-03 Aram Ter-Sarkisov

Hillclimbing is an essential part of any optimization algorithm. An important benchmark for hillclimbing algorithms on pseudo-Boolean functions $f: \{0,1\}^n \to \mathbb{R}$ are (strictly) montone functions, on which a surprising number of…

Probability · Mathematics 2018-08-06 Johannes Lengler , Anders Martinsson , Angelika Steger