Outputs (3)

On the Utility of Probing Trajectories for Algorithm-Selection (2024)
Presentation / Conference Contribution
Renau, Q., & Hart, E. (2024, April). On the Utility of Probing Trajectories for Algorithm-Selection. Presented at EvoStar 2024, Aberystwyth, UK

Machine-learning approaches to algorithm-selection typically take data describing an instance as input. Input data can take the form of features derived from the instance description or fitness landscape , or can be a direct representation of the ins... Read More about On the Utility of Probing Trajectories for Algorithm-Selection.

Improving Algorithm-Selection and Performance-Prediction via Learning Discriminating Training Samples (2024)
Presentation / Conference Contribution
Renau, Q., & Hart, E. (2024, July). Improving Algorithm-Selection and Performance-Prediction via Learning Discriminating Training Samples. Presented at GECCO 2024, Melbourne, USA

The choice of input-data used to train algorithm-selection models is recognised as being a critical part of the model success. Recently, feature-free methods for algorithm-selection that use short trajec-tories obtained from running a solver as input... Read More about Improving Algorithm-Selection and Performance-Prediction via Learning Discriminating Training Samples.

Towards optimisers that `Keep Learning' (2023)
Presentation / Conference Contribution
Hart, E., Miguel, I., Stone, C., & Renau, Q. (2023). Towards optimisers that `Keep Learning'. In GECCO '23 Companion: Proceedings of the Companion Conference on Genetic and Evolutionary Computation (1636-1638). https://doi.org/10.1145/3583133.3596344

We consider optimisation in the context of the need to apply an optimiser to a continual stream of instances from one or more domains, and consider how such a system might 'keep learning': by drawing on past experience to improve performance and lear... Read More about Towards optimisers that `Keep Learning'.