The Rolling Tide Evolutionary Algorithm: A Multi-Objective Optimiser for Noisy Optimisation Problems
- Submitting institution
-
University of Exeter
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1760
- Type
- D - Journal article
- DOI
-
10.1109/TEVC.2014.2304415
- Title of journal
- IEEE Transactions on Evolutionary Computation
- Article number
- -
- First page
- 103
- Volume
- 19
- Issue
- 1
- ISSN
- 1089-778X
- Open access status
- Out of scope for open access requirements
- Month of publication
- February
- Year of publication
- 2014
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
1
- Research group(s)
-
-
- Citation count
- 20
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The difficulty of multi-objective optimisation of black-box systems is compounded when noise is present in the objective functions, meaning even the partial order imposed by Pareto dominance-comparisons can be in error, impeding convergence. We develop a framework to efficiently use an accumulative resampling approach to mitigate the effect, exploiting a novel data-structure. This work led the lead author to commence the annual workshop series on Evolutionary Algorithms for Problems with Uncertainty at ACM GECCO, and fed into grant awards optimising noisy/data-driven problems, including Innovate UK 104400 (£262,482) on rapid calibration of digital twins (Laurence Oakes-Ash, City Science, loa@cityscience.com).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -