[Event at CIG] CFP: EvoLearn 2027 - First International Conference on Evolutionary Computation and Learning (part of EvoStar)

[Marc Schoenauer]

Please distribute widely - Apologies for cross-posting 

Call for papers for EvoLearn 2027 , the first International Conference on Evolutionary Computation and Learning (part of EvoStar) 

EvoLearn webpage: [ https://www.evostar.org/2027/evolearn | https://www.evostar.org/2027/evolearn/ ] 
Submission deadline: 1 November 2026 
Conference: 31 March – 2 April 2027, Mainz, Germany. 

Accepted papers will be presented orally or as posters at the event and included in the EvoLearn proceedings published by Springer Nature in a dedicated volume of the LNCS series. 
------------------------------------------------ 


The fields of Evolutionary Computation (EC) and Machine Learning (ML) have always been tightly intertwined. At the metaphoric level, evolution can be viewed as learning and adapting at the species time scale, while ML acts at the individual scale. At the algorithmic level, both EC and ML fields somehow search for models to fit some available data. Supervised and unsupervised learning aims at fitting available data and generalizing well to unseen data, while reinforcement learning aims at maximizing some reward in a given context. Evolutionary Computation focuses on high-quality regions of a search space defined by a fitness function. 



In this context, the incredible blossoming of ML in recent years, which has impacted all research domains, has particularly resonated in the EC community, opening new research opportunities in both fields. The use of ML techniques within EC algorithms, and meta-heuristics at large, is not new, but the tremendous recent progresses of ML have immediatly led to progresses in EC, from online hyperparameter adaptation to powerful surrogate modeling. On the other hand, beyond classical optimization techniques used in ML, there has always been some space for EC methods to successfully tackle problems out of reach of standard techniques, from minimizing non-differentiable losses to optimizing hyperparameters of ML pipelines and to searching rich unstructured search spaces, e.g., in Neural Architecture Search. 

EvoStar is hence launching EvoLearn, a new conference whose first edition will take place under the umbrella of EvoStar 2027 in Mainz, 31 March - 2nd April, with submission deadline on Nov. 1st. All details on EvoStar web site at [ https://www.evostar.org/2027/evolearn/ | https://www.evostar.org/2027/evolearn/ ] . 



EvoLearn is particularly interested in, but not limited to, original theoretical and/or experimental works combining one way or another evolutionary computation and machine learning. Some examples are EC for fine-tuning of ML models, hyperparameter optimization, prompt and pre-prompt optimization, or neural architecture search, as well as ML for metaheuristic algorithm selection and configuration, evolutionary variation operators or representations, surrogate modeling, or linkage learning. Beyond such recombination, EvoLearn also welcomes contributions to theory, methodology or application of EC from the point of view of learning at the population level. 

Like the other EvoStar events, EvoLearn aims at creating an inclusive, respectful conference environment that invites participation from people of all races, ethnicities, genders, ages, abilities, religions (or lack thereof), and sexual orientation. We actively seek to increase the diversity of our attendees, speakers, and sponsors. 
Being located in Europe makes it easy for researchers from other parts of the world to participate independently of political tensions. To reach a high level of inclusiveness and to be environmentally-friendly, we use a hybrid format making it easy to participate from abroad. The conference proceedings will be published by Springer Nature, within the EvoStar proceedings. 

We look forward to seeing you at EvoLearn 2027 in Mainz! 

The EvoLearn 2027 chairs 
Franz Rothlauf 
Marc Schoenauer 
Giorgia Nadizar (publication chair)