Nine Papers Accepted at GECCO 2024

Bridging Functions Across Domains

Transfer Learning of Surrogate Models via Domain Affine Transformation

Shuaiqun Pan, Diederick Vermetten, Manuel López-Ibáñez, Thomas Bäck, Hao Wang

This paper introduces a novel method for transferring surrogate models between different tasks, potentially revolutionizing how we approach optimization problems. It shows that with a small dataset from the target domain, the adapted model outperforms both the original surrogate and a new one built from scratch.

Benchmarking

Large-Scale Benchmarking of Metaphor-Based Optimization Heuristics

Diederick Vermetten, Carola Doerr, Hao Wang, Anna V. Kononova, Thomas Bäck

This research provides a comprehensive benchmarking of 294 algorithm implementations, spotlighting the importance of rigorous benchmarking and the hidden potential within metaphor-based algorithms.

Symbolic Regression

A Functional Analysis Approach to Symbolic Regression

Kirill Antonov, Roman Kalkreuth, Kaifeng Yang, Thomas Bäck, Niki van Stein, and Anna V Kononova

Our team offers a novel algorithm—Fourier Tree Growing (FTG)—that advances traditional genetic programming methods for symbolic regression, demonstrating significant performance improvements.

Innovating Green Logistics

A Corridor Model Evolutionary Algorithm for Fast Converging Green Vehicle Routing Problem

Ananta Anil Shahane, Niki van Stein, Yingjie Fan

This paper proposes a fresh approach to the vehicle routing problem, emphasizing speed and environmental friendliness, marking a substantial stride in the quest for efficient and sustainable logistics solutions.

Automated Algorithm Selection

Impact of Training Instance Selection on Automated Algorithm Selection Models for Numerical Black-box Optimization

Konstantin Dietrich, Diederick Vermetten, Carola Doerr, Pascal Kerschke

This work proposes a novel Automated Algorithm Selection pipeline and analysis based on a large number of 2 and 5 dimensional functions of the Many-Affine BBOB suite combined with exploratory landscape analysis features.

Genetic Programming Software

CGP++ : A Modern C++ Implementation of Cartesian Genetic Programming

Roman Kalkreuth, Thomas Bäck

This work proposes a modern implementation of Cartesian Genetic Programming.

Multi-objective Evolutionary Algorithms

What performance indicator to use for self-adaptation in Multi-objective evolutionary algorithms

Furong Ye, Frank Neumann, Jacob de Nobel, Aneta Neumann, Thomas Bäck

A comprehensive benchmarking study on self-adaptive mutation rates for multi-objective evolutionary algorithms.

Demistifying Nature-inspired Metaphors

A Critical Analysis of Raven Roost Optimization

Martijn Halsema, Diederick Vermetten, Thomas Bäck, Niki van Stein

This study critically examines the Raven Roost Optimization (RRO) algorithm within the broader context of nature-inspired metaheuristics, challenging its novelty and efficacy in the field of black-box optimization.

Modular Framework for Multi-objective Optimization

Modular Optimization Framework for Mixed Expensive and Inexpensive Real-World Problems

Roy de Winter, Thomas Bäck, Niki van Stein

A modular optimization framework is proposed that can deal with different problem characteristics encountered in real-world design problems. The common denominator of problems considered in this work is the computationally demanding objective function used to evaluate the designs, while some of the constraint functions can be inexpensive.

Parallel Multi-Objective Optimization for Expensive and Inexpensive Objectives and Constraints

Roy de Winter, Bas Milatz, Julian Blank, Niki van Stein, Thomas Bäck, Kalyanmoy Deb

Expensive objectives and constraints are key characteristics of real-world multi-objective optimization problems. In practice, they often occur jointly with inexpensive objectives and constraints. This paper presents the Inexpensive Objectives and Constraints Self-Adapting Multi-Objective Constraint Optimization algorithm that uses Radial Basis function Approximations (IOC-SAMO-COBRA) for such problems.