Back to List
Prof. Manuel López-Ibáñez
Modern high-performing algorithms for Optimization and Machine Learning are often the result of the careful composition of diverse algorithmic ideas. Often such algorithms are designed by human experts guided by their expertise and laborious trial-and-error. Nowadays, it is possible to automatically design such algorithms by combining flexible algorithmic frameworks and general-purpose hyper-parameter optimizers. In this talk, we will explain the general principles behind this automatic design approach and illustrate its use with several examples. We will also discuss how LLMs may represent (or not) the next evolution of this component-wise design approach.
Manuel López-Ibáñez is Full Professor (Chair) of Optimization at the Alliance Manchester Business School, University of Manchester, UK. He is Editor-in-Chief of ACM Transactions on Evolutionary Learning and Optimization, Associate Editor of the Evolutionary Computation journal and IEEE Transactions on Evolutionary Computation and Editorial Board Member of the Artificial Intelligence Journal and European Journal of Operational Research. Prof. López-Ibáñez has published more than 100 papers in international peer-reviewed journals and conferences on topics that include stochastic local search, black-box optimization, empirical reproducibility, multi-objective and interactive optimization algorithms for continuous and combinatorial problems, and the automatic configuration and design of optimization algorithms. https://lopez-ibanez.eu/
VIDEO: it will published after the presentation.
