Here is an overview:
- Introduction by the Guest Editors, Kevin Tierney and Meinolf Sellmann.
- Combining Multi-Objective Bayesian Optimization with Reinforcement Learning for TinyML Mark Deutel, Georgios Kontes, Christopher Mutschler and Jürgen Teich: „Deploying deep neural networks (DNNs) on microcontrollers (TinyML) is a common trend to process the increasing amount of sensor data generated at the edge, but in practice, resource and latency constraints make it difficult to find optimal DNN candidates. Neural architecture search (NAS) is an excellent approach to automate this search..„
- Enhancing Batch Diversity in Surrogate Optimization: A Determinantal Point Processes Approach. Nazanin Nezami, Hadis Anahideh: The exploration–exploitation tradeoff poses a significant challenge in surrogate optimization for expensive black-box functions, particularly when dealing with batch evaluation settings. Despite efforts to develop batch sampling techniques ...
- Hardening Active Directory Graphs via Evolutionary Diversity Optimization-based Policies. Diksha Goel, Max Ward, Aneta Neumann, Frank Neuman, Hung Nguyen, Mingyu Guo: Active Directory (AD) is the default security management system for Windows domain networks. An AD environment can be described as a cyber-attack graph, with nodes representing computers, accounts, and so forth, and edges indicating existing accesses…
- Learning to Cut Generation in Branch-and-Cut Algorithms for Combinatorial Optimization. Trang Vo, Mourad Baiou, Viet Hung Nguyen, Paul Weng: Branch-and-cut is one of the most successful methods to exactly solve combinatorial optimization problems. A key decision problem in branch-and-cut is cut generation—the problem of deciding whether to generate cuts or to branch at each node …
- RunAndSchedule2Survive: Algorithm Scheduling Based on Run2Survive. Valentin Margraf, Tom Koerner, Alexander Tornede, Marcel Wever: The algorithm selection problem aims to identify the most suitable algorithm for a given problem instance under specific time constraints, where suitability typically refers to a performance metric such as algorithm runtime …
- Surrogate Modeling to Address the Absence of Protected Membership Attributes in Fairness Evaluation. Serdar Kadioglu, Melinda Thielbar: It is imperative to ensure that AI models perform well for all groups including those from underprivileged populations. By comparing the performance of models for the protected group with respect to the rest of the population, we can…
The Special Issue on Learning and Intelligent Optimization of the ACM Transactions on Evolutionary Learning and Optimization is now available at https://dl.acm.org/toc/telo/2025/5/3