Prof. Celso C. Ribeiro

Universidade Federal Fluminense, Brazil

Celso C. Ribeiro has a bachelor’s degree in electrical engineering (1976) and a masters in systems engineering (1978). His main research areas include Combinatorial Optimization, Algorithm Design, Metaheuristics, and Sports Scheduling. He obtained a doctorate in Computer Science at École Nationale Supérieure des Télécommunications (France, 1983) and the Habilitation (HDR) at Université Paris 13 (France, 1990). Celso Ribeiro chaired the Departments of Electrical Engineering (1983-1987) and Computer Science (1993-1995) of the Catholic University of Rio de Janeiro. He coordinated the graduate program in Computer Science of Universidade Federal Fluminense (2009-2017), Brazil, where he is a Full Professor. Dr. Ribeiro also chaired the Department of Modernization Programs of the Brazilian Ministry of Education (2005-2007) and acted as Subsecretary of Education of the State of Rio de Janeiro (2007-2008), Brazil. He was President of the Brazilian Operations Research Society (SOBRAPO, 1989-1990), President of the Latin-American Association of Operations Research Societies (ALIO, 1992-1994), and Regional Vice-President of the International Federation of Operational Research Societies (IFORS, 1998-2000). He co-authored the books "Combinatorial Models for Scheduling Sports Tournaments" (2023) and "Optimization by GRASP: Greedy Randomized Adaptive Search Procedures" (2016), both published by Springer. He is the editor of four books and the author of more than 160 papers in international journals and 22 book chapters. He holds two US patents and has supervised 32 doctorate dissertations and 39 master theses. He is the General Editor of the journal International Transactions in Operational Research (since 2007) and a member of the editorial board of several journals such as Engineering Applications of Artificial Intelligence, Discrete Optimization, Journal of Heuristics, and RAIRO Operations Research. He was also the Editor-in-Chief of the Journal of the Brazilian Computing Society (2014-2015). Dr. Ribeiro is a member of the Brazilian Academy of Sciences. He was awarded the title of Doctor Honoris Causa by Universidad Nacional de San Agustin de Arequipa (Peru, 2010) and the Medal of the National Order of Scientific Merit (Brazil, 2018).

Prof. Andries Engelbrecht

Stellenbosch University, South Africa

Speech Title: Multi-Guide Particle Swarm Optimization: An Efficient Approach to Multi- and Many-Objective Optimization

Abstract: A number of particle swarm optimization (PSO) algorithms have been developed to solve multi-objective optimization problems (MOPs). However, most of these multi-objective PSO (MOPSO) algorithms are computationally complex, have a number of problem dependent control parameters, and do not scale well to many-objective optimization problems (MaOPs) and large-scale MOPs. This talk will present a recent MOPSO algorithm, the multi-guide PSO which makes use of sub-swarms to solve MOPs. Each sub-swarm optimizes one objective function independent of the other objectives, but exchanges information about all objectives via an archive guide selected from the set of non-dominated solutions. The result is a computationally efficient MOPSO algorithm, which has been shown to outperform state-of-the-art MOPSO algorithms and multi-objective evolutionary algorithms. In addition, the sub-swarm approach facilitates scalability to many-objectives without having to change the core algorithm to cope withe the consequences of having to optimize many objectives. Again, results will show that the MGPSO performs better than algorithms purposefully designed to solve MaOPS. While the MGPSO does introduce additional control parameters, the algorithm is the only MOPSO with formal theoretical analysis of conditions on the control parameters that will guarantee that an equilibrium state will be reached. These conditions have been used to develop a stability guided MGPSO that does not require time consuming tuning of its control parameters. Results will be presented to showcase the value of the MGPSO for solving MOPs and MaOPs.

Biography: Andries Engelbrecht received the Masters and PhD degrees in Computer Science from the University of Stellenbosch, South Africa, in 1994 and 1999 respectively. He is currently appointed as the Voigt Chair in Data Science in the Department of Industrial Engineering, with a joint appointment as Professor in the Computer Science Division, Stellenbosch University. Prior to 2019, he was appointed appointed in the Department of Computer Science, University of Pretoria (1998-2018), where he served as the head of the department (2008–2017), South African Research Chair in Artificial Intelligence (2007–2018), and Director of the Institute for Big Data and Data Science (2017–2018). His research interests include swarm intelligence, evolutionary computation, artificial neural networks, artificial immune systems, machine learning, data analytics, and the application of these Artificial Intelligence paradigms to data mining, games, bioinformatics, finance, and difficult optimization problems. He is author of two books, “Computational Intelligence: An Introduction” and “Fundamentals of Computational Swarm Intelligence”.


Dr. Abhishek Gupta

Agency for Science, Technology and Research (A*STAR), Singapore

Speech Title: Transfer optimization of expensive objective functions

Abstract: Advances at the intersection of optimization and machine learning promise new avenues for the efficient discovery of diverse yet high-quality engineering solutions. However, unlike many commercial applications where data is abundant, engineering problems are often characterized by data scarcity – requiring expensive numerical simulations and/or complex real-world procedures to acquire data. This attribute reduces the impact potential of modern generative algorithms that are known to be data hungry. As an alternative, transfer optimization promises a novel approach to the sample-efficient discovery of near-optimal solutions to a target optimization task by utilizing experiential priors from a relatively small number of related source tasks. In this talk, I shall present some recent algorithmic developments in the area of transfer optimization, applicable to both single- and multi-objective optimization problems. The algorithms under consideration will leverage ideas from probabilistic model-based search, with particular emphasis on evolutionary computation and surrogate-assisted optimization. Examples of the practical utility of these algorithms shall be showcased in domains including manufacturing and complex design.

Biography: Abhishek Gupta received the Ph.D. in Engineering Science from the University of Auckland, New Zealand, in 2014. He is a Scientist at the Agency for Science, Technology and Research (A*STAR) Singapore and has held prior appointments as Research Scientist at the Nanyang Technological University, Singapore. Abhishek has diverse research experience in the fields of computational science and computational intelligence, with recent research interest at the intersection of optimization, neuroevolutionary algorithms, probabilistic model-based methods and scientific machine learning. He received the 2019 and the 2023 IEEE Transactions on Evolutionary Computation Outstanding Paper Awards for pioneering work on the theory and algorithms of multitask evolutionary computation. He was also recognized as the 2021 IEEE Transactions on Emerging Topics of Computational Intelligence Outstanding Associate Editor. Abhishek is currently also an Associate Editor of the IEEE Transactions on Evolutionary Computation, and on the Editorial Boards of Complex & Intelligent Systems, Memetic Computing, and the Springer Book Series on Adaptation, Learning, and Optimization. He is an IEEE Senior Member and founding chair of the IEEE CIS Task Force on Multitask Learning and Multitask Optimization.