MétaCan
Menu
Back to cohort
Record W4402687508 · doi:10.2514/6.2024-4405

Gradient-Enhanced Bayesian Optimization With Application to Aerodynamic Shape Optimization

2024· article· en· W4402687508 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicAdvanced Multi-Objective Optimization Algorithms
Canadian institutionsInstitute for Christian StudiesUniversity of Toronto
Fundersnot available
KeywordsBayesian optimizationAerodynamicsComputer scienceBayesian probabilityShape optimizationMathematical optimizationArtificial intelligenceMathematicsAerospace engineeringEngineeringFinite element methodStructural engineering

Abstract

fetched live from OpenAlex

Bayesian optimizers have several desirable properties that make them well suited for various aerodynamic shape optimization applications. For example, the design space can often be multimodal, and Bayesian optimizers are efficient global optimizers. Bayesian optimizers also enable the use of mixed-fidelity data, the use of inexact function and gradient evaluations, and uncertainty quantification thanks to their use of probabilistic surrogates. The challenges of applying a Bayesian optimizer to aerodynamic shape optimization problems include the high-dimensional design space, the nonlinear constraints, and their limited application to local optimization. A local optimization framework for a gradient-enhanced Bayesian optimizer is developed in this paper that is shown to be competitive with the popular quasi-Newton based optimizer SNOPT for the nonlinearly constrained aerodynamic shape optimization of a transonic airfoil. A recently developed preconditioning method is used to address the ill-conditioning of the gradient-enhanced covariance matrix, which enables the Bayesian optimizer to converge the optimality as deeply as SNOPT. With these developments, gradient-enhanced Bayesian optimization represents a versatile option for a wide range of challenging aerodynamic shape optimization problems, including unimodal and multimodal problems, and chaotic flows where calculating accurate gradients is challenging.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.141
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.002
Science and technology studies0.0000.000
Scholarly communication0.0000.002
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.005
GPT teacher head0.239
Teacher spread0.234 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it