Invited Speakers

Ideals and Realities of Benchmarking in Evolutionary Multiobjective Optimization

Research in Evolutionary Multiobjective Optimization (EMO) is motivated by real-world problems, which often involve conflicting objectives and complex constraints. Yet, benchmarking in EMO frequently neglects the needs of real-world applications, limiting the relevance and transferability of research findings. This talk will contrast the ideals of benchmarking with the realities observed in current practice. Drawing from insights gained through the study of real-world optimization problems, the presentation will highlight key mismatches between benchmark design and application demands, discuss what current platforms (like COCO) offer, and identify critical gaps that still need to be addressed. The goal is to encourage benchmarking practices that are better aligned with the challenges and diversity of real-world EMO problems.

Tea Tušar

Tea Tušar is a senior research associate at the Department of Intelligent Systems at the Jožef Stefan Institute and an assistant professor at the Jožef Stefan International Postgraduate School. She received her PhD for her work on visualizing solution sets in multi-objective optimization. Following her doctorate, she completed a postdoctoral fellowship at Inria Lille, France, where she contributed to benchmarking multi-objective optimization algorithms. Her work focuses on Evolutionary Computation, with a particular emphasis on visualizing and benchmarking the results of evolutionary algorithms for both single- and multi-objective optimization, with and without constraints, and applying these methods to solve real-world optimization problems. 

Tea has been involved in several collaborative projects that apply optimization techniques to practical challenges. These include optimizing electric motor designs, improving energy scheduling systems, and optimizing tunnel alignment. She has contributed to the development of the COCO platform (https://coco-platform.org/) for comparing optimization algorithms, expanding its capabilities to handle multi-objective and mixed-integer problems. Her work continues to focus on advancing optimization tools for both academic research and industrial applications.

She has held organizational and editorial roles at PPSN and GECCO and serves as an associate editor for Evolutionary Computation and ACM Transactions on Evolutionary Learning and Optimization. Since 2023, she has also been serving as the Vice President of ACM Slovenia.

Mathematical modelling, computational intelligence and machine learning in biomedicine: it takes (at least) three to tango

Dysfunctional cellular processes caused by molecular-level events can induce local and global damages – from cells to organs to the whole organism – often resulting in the onset of complex diseases. Understanding the finely orchestrated mechanisms of cellular regulation is thus indispensable to detect and possibly control any pathological state. In this context, the integration between biomedical data and computational tools is pivotal for an efficacious use of mathematical models, as a way to predict the emergent behaviour of biological systems in both physiological and altered conditions. On top of this, an open problem in most clinical scenarios is related to the personalization of therapeutic treatment for patients suffering from chronic or multifactorial diseases: despite the recognition that the “one size fits all” approach is no more reliable, population-based models are generally used in diagnosis and treatment decision-making.
In this talk, I will show how fuzzy logic-based models can be effectively exploited in biomedicine to analyse complex systems consisting in heterogeneous components, whose measurements can be obtained from multiple sources (omics data, imaging, etc.) and are generally characterized by uncertainty. Fuzzy logic interpretability makes it particularly suitable as a modelling formalism for clinical disciplines, as it facilitates fruitful communications and crosstalk with domain experts. Though, the identification of optimal treatments cannot be achieved by fuzzy models alone but demands the combination with computational intelligence and machine learning methods. I will present some examples of the way (multi-objective) optimization meta-heuristics and reinforcement learning can be coupled with fuzzy logic – and the other way round – in contexts ranging from cancer to autoimmune disorders.

Daniela Besozzi

Daniela Besozzi is associate professor at the Department of Informatics, Systems and Communication at the University of Milano-Bicocca, Italy, where she is also affiliated with the interdepartmental research centres “Bicocca Bioinformatics Biostatistics and Bioimaging Centre – B4” and “Bicocca Research Centre in Health Services – BReCHS”.

Her research is mainly focused on the mathematical modelling of complex biological systems – with a special interest in the cellular processes that lead to the onset and progression of multifactorial diseases – and the development of bioinformatics and artificial intelligence methods in medical disciplines, ranging from oncology to digital pathology. Her work contributed, among the others, to the identification of therapeutic targets in cancer cells and the screening for combination cancer therapies by means of fuzzy logic modelling and multi-objective optimization algorithms; the generation of a novel protocol to study cell proliferation in human acute myeloid leukemia xenografts by means of stochastic modelling and swarm intelligence meta-heuristics; and the development of a deep learning-based method for the morphometric characterization and multiclass segmentation of nuclei in thyroid lesions.

Daniela is co-author of more than 100 peer-reviewed works published in international journals, conference proceedings, and book chapters. She is co-inventor of a patented and CE-marked method to automatically predict the optimal patient-specific inversion time for late gadolinium enhancement imaging in cardiac magnetic resonance. She serves as associate editor for Frontiers in Systems Biology, section on Multiscale Mechanistic Modeling, and she is member of the IEEE CIS Task Force on “Advanced representation in biological and medical search and optimization”.

Daniela is an active member of the working group on gender equality at the University of Milano-Bicocca and contributed to editing the Gender Equality Plan (GEP). She is co-promoter of a pilot project to incentivize the enrolment of female students in STEM disciplines, and she regularly contributes to the organization of events related to the dissemination of knowledge, curiosity and passion about science and literature to the broader society. She has two cats.