DG2: A Faster and More Accurate Differential Grouping for Large-Scale Black-Box Optimization
- Submitting institution
-
The University of Leeds
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- UOA11-4056
- Type
- D - Journal article
- DOI
-
10.1109/TEVC.2017.2694221
- Title of journal
- IEEE Transactions on Evolutionary Computation
- Article number
- -
- First page
- 929
- Volume
- 21
- Issue
- 6
- ISSN
- 1089-778X
- Open access status
- Compliant
- Month of publication
- April
- Year of publication
- 2017
- 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
-
4
- Research group(s)
-
B - AI (Artificial Intelligence)
- Citation count
- 81
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper presents the most accurate variable interaction analysis algorithm of its time. For the first time, it uses rigorous error analysis to find bounds on computational error and incorporates it into the interaction detection process resulting in significant improvement in its robustness to computational error. The paper also proves the lower bound on the number of function evaluations needed to identify a complete interaction matrix of a function. It forms the basis for other state-of-the-art algorithms including the winner of IEEE CEC-2019 large-scale global optimization competition (co-authored by Omidvar). Contributed to winning Australian Research Council Discovery Grant (DP180101170).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
