Marcus Gallagher
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Marcus Gallagher has a total of 111 co-authors. Here are the top co-authors by number of shared publications:
- Bo Yuan
School of Electrical Engineering and Computer Science, The University of Queensland, Brisbane, QLD, Australia
12 shared publications - Jason P. Connor
National Centre for Youth Substance Use Research, The University of Queensland, St Lucia, Australia
5 shared publications - Wei Luo
Deakin University
5 shared publications - Michael J. Drinkwater
School of Mathematics and Physics, The University of Queensland, Brisbane, QLD 4072, Australia
4 shared publications Michelle McPartland
University of Queensland, St Lucia, Australia
4 shared publicationsRachael Morgan
University of Queensland
4 shared publications
Latest Publications
- 2 September 2026
- Published by Springer Nature
- p. 471-486
Modularity-Based Linkage Model Assisted Gradient Descent for Neural Network Training
- 2 September 2026
- Published by Springer Nature
- p. 471-486
Modularity-Based Linkage Model Assisted Gradient Descent for Neural Network Training
- Open Access
SimTO: A simulation-based topology optimization framework for bespoke soft robotic grippers
Soft robotic grippers are essential for grasping delicate, geometrically complex objects in manufacturing, healthcare and agriculture. However, existing grippers struggle to grasp feature-rich objects with high topological variability, including gears with sharp tooth profiles on automotive assembly lines, corals with fragile protrusions, or vegetables with irregular branching structures like broccoli. Unlike simple geometric primitives such as cubes or spheres, feature-rich objects lack a clear "optimal" contact surface, making them both difficult to grasp and susceptible to damage when grasped by existing gripper designs. Safe handling of such objects therefore requires specialized soft grippers whose morphology is tailored to the object's features. Topology optimization offers a promising approach for producing specialized grippers, but its utility is limited by the requirement for pre-defined load cases. For soft grippers interacting with feature-rich objects, these loads arise from hundreds of unpredictable gripper-object contact forces during grasping and are unknown a priori. To address this problem, we introduce SimTO, a framework that enables high-resolution topology optimization by automatically extracting load cases from a contact-based physics simulator, eliminating the need for manual load specification. Given an arbitrary feature-rich object, SimTO produces highly customized soft grippers with fine-grained morphological features tailored to the object geometry. Numerical results show our designs are not only highly specialized to feature-rich objects, but also generalize to unseen objects.
Open AccessSimTO: A simulation-based topology optimization framework for bespoke soft robotic grippers
Soft robotic grippers are essential for grasping delicate, geometrically complex objects in manufacturing, healthcare and agriculture. However, existing grippers struggle to grasp feature-rich objects with high topological variability, including gears with sharp tooth profiles on automotive assembly lines, corals with fragile protrusions, or vegetables with irregular branching structures like broccoli. Unlike simple geometric primitives such as cubes or spheres, feature-rich objects lack a clear "optimal" contact surface, making them both difficult to grasp and susceptible to damage when grasped by existing gripper designs. Safe handling of such objects therefore requires specialized soft grippers whose morphology is tailored to the object's features. Topology optimization offers a promising approach for producing specialized grippers, but its utility is limited by the requirement for pre-defined load cases. For soft grippers interacting with feature-rich objects, these loads arise from hundreds of unpredictable gripper-object contact forces during grasping and are unknown a priori. To address this problem, we introduce SimTO, a framework that enables high-resolution topology optimization by automatically extracting load cases from a contact-based physics simulator, eliminating the need for manual load specification. Given an arbitrary feature-rich object, SimTO produces highly customized soft grippers with fine-grained morphological features tailored to the object geometry. Numerical results show our designs are not only highly specialized to feature-rich objects, but also generalize to unseen objects.
- 27 November 2025
- Published by Springer Nature
- p. 69-80
Using Individual Problem Instances for Exploratory Black Box Optimisation Benchmarking: A Case Study Using XOR Neural Networks
- 27 November 2025
- Published by Springer Nature
- p. 69-80
Using Individual Problem Instances for Exploratory Black Box Optimisation Benchmarking: A Case Study Using XOR Neural Networks
- Open Access
- 27 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 297-307
A Standardized Benchmark Set of Clustering Problem Instances for Comparing Black-Box Optimizers
- 27 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 297-307
Open AccessA Standardized Benchmark Set of Clustering Problem Instances for Comparing Black-Box Optimizers
- Open Access
A Standardized Benchmark Set of Clustering Problem Instances for Comparing Black-Box Optimizers
One key challenge in optimization is the selection of a suitable set of benchmark problems. A common goal is to find functions which are representative of a class of real-world optimization problems in order to ensure findings on the benchmarks will translate to relevant problem domains. While some problem characteristics are well-covered by popular benchmarking suites, others are often overlooked. One example of such a problem characteristic is permutation invariance, where the search space consists of a set of symmetrical search regions. This type of problem occurs e.g. when a set of solutions has to be found, but the ordering within this set does not matter. The data clustering problem, often seen in machine learning contexts, is a clear example of such an optimization landscape, and has thus been proposed as a base from which optimization benchmarks can be created. In addition to the symmetry aspect, these clustering problems also contain potential regions of neutrality, which can provide an additional challenge to optimization algorithms. In this paper, we present a standardized benchmark suite for the evaluation of continuous black-box optimization algorithms, based on data clustering problems. To gain insight into the diversity of the benchmark set, both internally and in comparison to existing suites, we perform a benchmarking study of a set of modular CMA-ES configurations, as well as an analysis using exploratory landscape analysis. Our benchmark set is open-source and integrated with the IOHprofiler benchmarking framework to encourage its use in future research.
Open AccessA Standardized Benchmark Set of Clustering Problem Instances for Comparing Black-Box Optimizers
One key challenge in optimization is the selection of a suitable set of benchmark problems. A common goal is to find functions which are representative of a class of real-world optimization problems in order to ensure findings on the benchmarks will translate to relevant problem domains. While some problem characteristics are well-covered by popular benchmarking suites, others are often overlooked. One example of such a problem characteristic is permutation invariance, where the search space consists of a set of symmetrical search regions. This type of problem occurs e.g. when a set of solutions has to be found, but the ordering within this set does not matter. The data clustering problem, often seen in machine learning contexts, is a clear example of such an optimization landscape, and has thus been proposed as a base from which optimization benchmarks can be created. In addition to the symmetry aspect, these clustering problems also contain potential regions of neutrality, which can provide an additional challenge to optimization algorithms. In this paper, we present a standardized benchmark suite for the evaluation of continuous black-box optimization algorithms, based on data clustering problems. To gain insight into the diversity of the benchmark set, both internally and in comparison to existing suites, we perform a benchmarking study of a set of modular CMA-ES configurations, as well as an analysis using exploratory landscape analysis. Our benchmark set is open-source and integrated with the IOHprofiler benchmarking framework to encourage its use in future research.
- Open Access
- 14 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 135-138
Towards an Improved Understanding of Features for More Interpretable Landscape Analysis
Landscape analysis has received increasing attention in the literature, with a major focus on producing feature data to be used in a machine learning pipeline for automatic algorithm selection and configuration. In contrast, the original purpose of landscape analysis (i.e. to develop theory and techniques to understand the structure of fitness landscapes) has been somewhat overshadowed. This paper aims to clarify the purpose of landscape features, emphasizing the need for clear definitions of distance or similarity between optimization problem instances. It argues that current methodologies' shortcomings can be better understood from this perspective and advocates for more interpretable features and distances to gain explainable insights into problem instances, algorithm-problem mappings, and improved benchmarking of black-box algorithms.
- 14 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 135-138
Open AccessTowards an Improved Understanding of Features for More Interpretable Landscape Analysis
Landscape analysis has received increasing attention in the literature, with a major focus on producing feature data to be used in a machine learning pipeline for automatic algorithm selection and configuration. In contrast, the original purpose of landscape analysis (i.e. to develop theory and techniques to understand the structure of fitness landscapes) has been somewhat overshadowed. This paper aims to clarify the purpose of landscape features, emphasizing the need for clear definitions of distance or similarity between optimization problem instances. It argues that current methodologies' shortcomings can be better understood from this perspective and advocates for more interpretable features and distances to gain explainable insights into problem instances, algorithm-problem mappings, and improved benchmarking of black-box algorithms.
- Open Access
- 14 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1520-1526
Analyzing the Runtime of the Gene-pool Optimal Mixing Evolutionary Algorithm (GOMEA) on the Concatenated Trap Function
The Gene-pool Optimal Mixing Evolutionary Algorithm (GOMEA) is a state of the art evolutionary algorithm that leverages linkage learning to efficiently exploit problem structure. By identifying and preserving important building blocks during variation, GOMEA has shown promising performance on various optimization problems. In this paper, we provide the first runtime analysis of GOMEA on the concatenated trap function, a challenging benchmark problem that consists of multiple deceptive subfunctions. We derived an upper bound on the expected runtime of GOMEA with a truthful linkage model, showing that it can solve the problem in O(m3 2k) with high probability, where m is the number of subfunctions and k is the subfunction length. This is a significant speedup compared to the (1+1) EA, which requires O(ln(m)(mk)k) expected evaluations.
- 14 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1520-1526
Open AccessAnalyzing the Runtime of the Gene-pool Optimal Mixing Evolutionary Algorithm (GOMEA) on the Concatenated Trap Function
The Gene-pool Optimal Mixing Evolutionary Algorithm (GOMEA) is a state of the art evolutionary algorithm that leverages linkage learning to efficiently exploit problem structure. By identifying and preserving important building blocks during variation, GOMEA has shown promising performance on various optimization problems. In this paper, we provide the first runtime analysis of GOMEA on the concatenated trap function, a challenging benchmark problem that consists of multiple deceptive subfunctions. We derived an upper bound on the expected runtime of GOMEA with a truthful linkage model, showing that it can solve the problem in O(m3 2k) with high probability, where m is the number of subfunctions and k is the subfunction length. This is a significant speedup compared to the (1+1) EA, which requires O(ln(m)(mk)k) expected evaluations.
- Open Access
- 14 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 139-142
Searching for Benchmark Problem Instances from Data-Driven Optimisation
Given the large number of existing metaheuristic optimisation algorithms, there has been an increasing focus on improving benchmarking practices, to gain an improved understanding empirical performance, as well as matching algorithms and problems. One important aspect of this more diversity in test problem sets so that algorithms are evaluated on a wider range of problem instances, including problems that are more real-world representative. In this paper, we explore data-driven benchmarking problems. By perturbing the data, we perform meta-search over this space of problem instances. Specifically, we consider sum of squares clustering problems and find instances that test CMA-ES. This approach can be effective, even when the dataset is very simple. In addition, we show that simple clustering instances have interesting properties, including neutrality (missing from many commonly-used benchmarks). We argue that data-driven optimisation can provide useful insights into problem structure and algorithm behaviour.
- 14 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 139-142
Open AccessSearching for Benchmark Problem Instances from Data-Driven Optimisation
Given the large number of existing metaheuristic optimisation algorithms, there has been an increasing focus on improving benchmarking practices, to gain an improved understanding empirical performance, as well as matching algorithms and problems. One important aspect of this more diversity in test problem sets so that algorithms are evaluated on a wider range of problem instances, including problems that are more real-world representative. In this paper, we explore data-driven benchmarking problems. By perturbing the data, we perform meta-search over this space of problem instances. Specifically, we consider sum of squares clustering problems and find instances that test CMA-ES. This approach can be effective, even when the dataset is very simple. In addition, we show that simple clustering instances have interesting properties, including neutrality (missing from many commonly-used benchmarks). We argue that data-driven optimisation can provide useful insights into problem structure and algorithm behaviour.
- Open Access
- 2 January 2024
- Published by Elsevier in Journal of Information Security and Applications
- Vol. 80
Benchmarking the benchmark — Comparing synthetic and real-world Network IDS datasets
- 2 January 2024
- Published by Elsevier in Journal of Information Security and Applications
- Vol. 80
Open AccessBenchmarking the benchmark — Comparing synthetic and real-world Network IDS datasets
- 2 October 2023
- Published by University of Queensland Library
Multi-layer Perceptron Error Surfaces: Visualization, Structure and Modelling
The University of Queensland's institutional repository, UQ eSpace, aims to create global visibility and accessibility of UQ’s scholarly research.
- 2 October 2023
- Published by University of Queensland Library
Multi-layer Perceptron Error Surfaces: Visualization, Structure and Modelling
The University of Queensland's institutional repository, UQ eSpace, aims to create global visibility and accessibility of UQ’s scholarly research.