English
Related papers

Related papers: Frequency Fitness Assignment: Making Optimization …

200 papers

A fitness assignment process transforms the features (such as the objective value) of a candidate solution to a scalar fitness, which then is the basis for selection. Under Frequency Fitness Assignment (FFA), the fitness corresponding to an…

Neural and Evolutionary Computing · Computer Science 2022-05-26 Thomas Weise , Zhize Wu , Xinlu Li , Yan Chen , Jörg Lässig

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

Linear functions play a key role in the runtime analysis of evolutionary algorithms and studies have provided a wide range of new insights and techniques for analyzing evolutionary computation methods. Motivated by studies on separable…

Neural and Evolutionary Computing · Computer Science 2022-08-12 Frank Neumann , Carsten Witt

This paper extends the runtime analysis of non-elitist evolutionary algorithms (EAs) with fitness-proportionate selection from the simple OneMax function to the linear functions. Not only does our analysis cover a larger class of fitness…

Neural and Evolutionary Computing · Computer Science 2019-08-26 Duc-Cuong Dang , Anton Eremeev , Per Kristian Lehre

For genetic algorithms using a bit-string representation of length~$n$, the general recommendation is to take $1/n$ as mutation rate. In this work, we discuss whether this is really justified for multimodal functions. Taking jump functions…

Neural and Evolutionary Computing · Computer Science 2017-03-23 Benjamin Doerr , Huu Phuoc Le , Régis Makhmara , Ta Duy Nguyen

Jump functions are the {most-studied} non-unimodal benchmark in the theory of randomized search heuristics, in particular, evolutionary algorithms (EAs). They have significantly improved our understanding of how EAs escape from local…

Neural and Evolutionary Computing · Computer Science 2024-10-08 Henry Bambury , Antoine Bultel , Benjamin Doerr

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

It is known that the evolutionary algorithm $(1+1)$-EA with mutation rate $c/n$ optimises every monotone function efficiently if $c<1$, and needs exponential time on some monotone functions (HotTopic functions) if $c\geq 2.2$. We study the…

Neural and Evolutionary Computing · Computer Science 2018-03-29 Johannes Lengler

To gain a better theoretical understanding of how evolutionary algorithms (EAs) cope with plateaus of constant fitness, we propose the $n$-dimensional Plateau$_k$ function as natural benchmark and analyze how different variants of the $(1 +…

Neural and Evolutionary Computing · Computer Science 2021-11-02 Denis Antipov , Benjamin Doerr

While most theoretical run time analyses of discrete randomized search heuristics provide bounds on the expected number of evaluations to find the global optimum, we consider the anytime performance of evolutionary and…

Neural and Evolutionary Computing · Computer Science 2026-04-09 Timo Kötzing , Jurek Sander

The $(1 + (\lambda,\lambda))$ genetic algorithm is a younger evolutionary algorithm trying to profit also from inferior solutions. Rigorous runtime analyses on unimodal fitness functions showed that it can indeed be faster than classical…

Neural and Evolutionary Computing · Computer Science 2022-06-17 Denis Antipov , Benjamin Doerr , Vitalii Karavaev

Repair operators are often used for constraint handling in constrained combinatorial optimization. We investigate the (1+1)~EA equipped with a tailored jump-and-repair operation that can be used to probabilistically repair infeasible…

Neural and Evolutionary Computing · Computer Science 2023-01-24 Luke Branson , Andrew M. Sutton

We consider the expected runtime of non-elitist evolutionary algorithms (EAs), when they are applied to a family of fitness functions with a plateau of second-best fitness in a Hamming ball of radius r around a unique global optimum. On one…

Neural and Evolutionary Computing · Computer Science 2020-08-20 Anton V. Eremeev

The one-fifth success rule is one of the best-known and most widely accepted techniques to control the parameters of evolutionary algorithms. While it is often applied in the literal sense, a common interpretation sees the one-fifth success…

Neural and Evolutionary Computing · Computer Science 2021-12-30 Benjamin Doerr , Carola Doerr , Johannes Lengler

In real-world applications, many optimization problems have the time-linkage property, that is, the objective function value relies on the current solution as well as the historical solutions. Although the rigorous theoretical analysis on…

Neural and Evolutionary Computing · Computer Science 2021-02-25 Weijie Zheng , Huanhuan Chen , Xin Yao

Feature transformation for AI is an essential task to boost the effectiveness and interpretability of machine learning (ML). Feature transformation aims to transform original data to identify an optimal feature space that enhances the…

Machine Learning · Computer Science 2023-01-03 Meng Xiao , Dongjie Wang , Min Wu , Ziyue Qiao , Pengfei Wang , Kunpeng Liu , Yuanchun Zhou , Yanjie Fu

In the federated learning setting, multiple clients jointly train a model under the coordination of the central server, while the training data is kept on the client to ensure privacy. Normally, inconsistent distribution of data across…

Machine Learning · Computer Science 2020-12-21 Wei Huang , Tianrui Li , Dexian Wang , Shengdong Du , Junbo Zhang

Evolutionary algorithms are bio-inspired algorithms that can easily adapt to changing environments. Recent results in the area of runtime analysis have pointed out that algorithms such as the (1+1)~EA and Global SEMO can efficiently…

Neural and Evolutionary Computing · Computer Science 2022-06-07 Vahid Roostapour , Aneta Neumann , Frank Neumann

We propose and analyze a self-adaptive version of the $(1,\lambda)$ evolutionary algorithm in which the current mutation rate is part of the individual and thus also subject to mutation. A rigorous runtime analysis on the OneMax benchmark…

Neural and Evolutionary Computing · Computer Science 2018-12-03 Benjamin Doerr , Carsten Witt , Jing Yang

The study of first-order optimization algorithms (FOA) typically starts with assumptions on the objective functions, most commonly smoothness and strong convexity. These metrics are used to tune the hyperparameters of FOA. We introduce a…

Machine Learning · Computer Science 2024-05-30 Charles Guille-Escuret , Baptiste Goujaud , Manuela Girotti , Ioannis Mitliagkas
‹ Prev 1 2 3 10 Next ›