Matches in SemOpenAlex for { <https://semopenalex.org/work/W4282920007> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W4282920007 endingPage "9833" @default.
- W4282920007 startingPage "9820" @default.
- W4282920007 abstract "Bayesian optimization (BO) is well known to be sample efficient for solving black-box problems. However, BO algorithms may get stuck in suboptimal solutions even with plenty of samples. Intrinsically, such a suboptimal problem of BO can attribute to the poor surrogate accuracy of the trained Gaussian process (GP), particularly that in the regions where the optimal solutions locate. Hence, we propose to build multiple GP models instead of a single GP surrogate to complement each other, thus resolving the suboptimal problem of BO. Nevertheless, according to the bias-variance tradeoff equation, the individual prediction errors can increase when increasing the diversity of models, which may lead even worse overall surrogate accuracy. On the other hand, based on the theory of the Rademacher complexity, it has been proven that exploiting the agreement of models on unlabeled information can reduce the complexity of hypothesis space, therefore achieving the required surrogate accuracy with fewer samples. Such value of model agreement has been extensively demonstrated for co-training style algorithms to boost model accuracy with a small portion of samples. Inspired by the above, we propose a novel BO algorithm labeled as co-learning BO (CLBO), which exploits both model diversity and agreement on unlabeled information to improve the overall surrogate accuracy with limited samples, therefore achieving more efficient global optimization. Through tests on five numerical toy problems and three engineering benchmarks, the effectiveness of the proposed CLBO has been well demonstrated." @default.
- W4282920007 created "2022-06-16" @default.
- W4282920007 creator A5024159747 @default.
- W4282920007 creator A5037219002 @default.
- W4282920007 creator A5059246379 @default.
- W4282920007 creator A5060723344 @default.
- W4282920007 date "2022-09-01" @default.
- W4282920007 modified "2023-10-16" @default.
- W4282920007 title "Co-Learning Bayesian Optimization" @default.
- W4282920007 doi "https://doi.org/10.1109/tcyb.2022.3168551" @default.
- W4282920007 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35687641" @default.
- W4282920007 hasPublicationYear "2022" @default.
- W4282920007 type Work @default.
- W4282920007 citedByCount "1" @default.
- W4282920007 countsByYear W42829200072023 @default.
- W4282920007 crossrefType "journal-article" @default.
- W4282920007 hasAuthorship W4282920007A5024159747 @default.
- W4282920007 hasAuthorship W4282920007A5037219002 @default.
- W4282920007 hasAuthorship W4282920007A5059246379 @default.
- W4282920007 hasAuthorship W4282920007A5060723344 @default.
- W4282920007 hasConcept C104317684 @default.
- W4282920007 hasConcept C107673813 @default.
- W4282920007 hasConcept C112313634 @default.
- W4282920007 hasConcept C11413529 @default.
- W4282920007 hasConcept C119857082 @default.
- W4282920007 hasConcept C121332964 @default.
- W4282920007 hasConcept C121955636 @default.
- W4282920007 hasConcept C126255220 @default.
- W4282920007 hasConcept C127716648 @default.
- W4282920007 hasConcept C131675550 @default.
- W4282920007 hasConcept C144133560 @default.
- W4282920007 hasConcept C154945302 @default.
- W4282920007 hasConcept C163716315 @default.
- W4282920007 hasConcept C185592680 @default.
- W4282920007 hasConcept C188082640 @default.
- W4282920007 hasConcept C196083921 @default.
- W4282920007 hasConcept C2778049539 @default.
- W4282920007 hasConcept C33923547 @default.
- W4282920007 hasConcept C41008148 @default.
- W4282920007 hasConcept C55493867 @default.
- W4282920007 hasConcept C61326573 @default.
- W4282920007 hasConcept C62520636 @default.
- W4282920007 hasConceptScore W4282920007C104317684 @default.
- W4282920007 hasConceptScore W4282920007C107673813 @default.
- W4282920007 hasConceptScore W4282920007C112313634 @default.
- W4282920007 hasConceptScore W4282920007C11413529 @default.
- W4282920007 hasConceptScore W4282920007C119857082 @default.
- W4282920007 hasConceptScore W4282920007C121332964 @default.
- W4282920007 hasConceptScore W4282920007C121955636 @default.
- W4282920007 hasConceptScore W4282920007C126255220 @default.
- W4282920007 hasConceptScore W4282920007C127716648 @default.
- W4282920007 hasConceptScore W4282920007C131675550 @default.
- W4282920007 hasConceptScore W4282920007C144133560 @default.
- W4282920007 hasConceptScore W4282920007C154945302 @default.
- W4282920007 hasConceptScore W4282920007C163716315 @default.
- W4282920007 hasConceptScore W4282920007C185592680 @default.
- W4282920007 hasConceptScore W4282920007C188082640 @default.
- W4282920007 hasConceptScore W4282920007C196083921 @default.
- W4282920007 hasConceptScore W4282920007C2778049539 @default.
- W4282920007 hasConceptScore W4282920007C33923547 @default.
- W4282920007 hasConceptScore W4282920007C41008148 @default.
- W4282920007 hasConceptScore W4282920007C55493867 @default.
- W4282920007 hasConceptScore W4282920007C61326573 @default.
- W4282920007 hasConceptScore W4282920007C62520636 @default.
- W4282920007 hasFunder F4320321001 @default.
- W4282920007 hasFunder F4320329860 @default.
- W4282920007 hasFunder F4320336864 @default.
- W4282920007 hasIssue "9" @default.
- W4282920007 hasLocation W42829200071 @default.
- W4282920007 hasLocation W42829200072 @default.
- W4282920007 hasOpenAccess W4282920007 @default.
- W4282920007 hasPrimaryLocation W42829200071 @default.
- W4282920007 hasRelatedWork W1723534789 @default.
- W4282920007 hasRelatedWork W2724199550 @default.
- W4282920007 hasRelatedWork W3035366775 @default.
- W4282920007 hasRelatedWork W3097730944 @default.
- W4282920007 hasRelatedWork W3128150010 @default.
- W4282920007 hasRelatedWork W3214603780 @default.
- W4282920007 hasRelatedWork W4237912051 @default.
- W4282920007 hasRelatedWork W4280525836 @default.
- W4282920007 hasRelatedWork W4287374055 @default.
- W4282920007 hasRelatedWork W4365800535 @default.
- W4282920007 hasVolume "52" @default.
- W4282920007 isParatext "false" @default.
- W4282920007 isRetracted "false" @default.
- W4282920007 workType "article" @default.