El Departamento de Informática de la Universidad Técnica Federico Santa María tiene el agrado de invitar a la comunidad Universitaria a su ciclo de coloquios 2023. La presentación se realizará en inglés, en la Sala F106 del Campus Casa Central con videoconferencia a la sala B038 (LPA) del Campus San Joaquín y transmisión en https://tv.inf.utfsm.cl/coloquio.
Participa, sin previa inscripción, asistiendo al lugar indicado o ingresando al enlace el día y hora del evento (enlace se actualiza al momento del coloquio)
Thomas Stützle, Research director of the Belgian F.R.S.-FNRS (National Science Foundation)
Thomas Stützle is a research director of the Belgian F.R.S.-FNRS (National Science Foundation) working at the IRIDIA laboratory of Université libre de Bruxelles (ULB), Belgium. He has co-authored three books among which are “Stochastic Local Search: Foundations and Applications” (Morgan Kaufmann) and “Ant Colony Optimization” (MIT Press), both being the main references in their respective areas. His other publications include more than 250 articles in journals, international conferences or edited books many of which are highly cited. In fact, his research contributions received so far more than 55,000 citations in Google Scholar and his h-index is 81. His main research interests are in stochastic local search algorithms, multi-objective optimization, and automatic design of algorithms.
The design and development algorithms can be time-consuming and difficult for a number of reasons including the complexity of the problems being tackled, the large number of degrees of freedom when designing an algorithm and setting its numerical parameters, and the difficulties of algorithm analysis due to heuristic biases and stochasticity. Still very often this design is done manually, mainly guided by the expertise and intuition of the algorithm designer. However, the advancement of automatic algorithm configuration methods offers new possibilities to make this process more automatic, avoid some methodological issues, and at the same time improve the performance of algorithms. In this talk, I will highlight the advantages of addressing algorithm design and configuration by algorithmic techniques; describe the main existing automatic algorithm design techniques; and discuss some of the main successful applications of automatic design we have in our own work. In particular, I will show how flexible algorithm frameworks can support the automatic design of high-performing hybrid stochastic local search algorithms. In fact, even for problems that have received very high attention in the literature new state-of-the-art algorithms can be obtained automatically, that is, without manual algorithm tuning. I will conclude arguing that automatic algorithm design will also have the power to transform the way algorithms for difficult problems are designed in the future