Multi-Objective Bayesian Optimization over High-Dimensional Search Spaces

Daulton, Samuel; Eriksson, David; Balandat, Maximilian; Bakshy, Eytan

doi:10.48550/arxiv.2109.10964

Cited by 7 publications

(11 citation statements)

References 27 publications

(42 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To avoid this issue, Eriksson et al (2019) introduced trust region Bayesian optimization (TRBO) that performs optimization in smaller trust regions that evolve across the search space. More recently, (MORBO) Daulton et al (2021) extended this work to the multi-objective setting. While MORBO handles high-dimensional parameter spaces well, Daulton et al (2021) only considered problems with few outcomes and non-composite settings.…”

Section: Composite Multi-objective Optimization Over High-dimensional...mentioning

confidence: 99%

“…More recently, (MORBO) Daulton et al (2021) extended this work to the multi-objective setting. While MORBO handles high-dimensional parameter spaces well, Daulton et al (2021) only considered problems with few outcomes and non-composite settings. In this work we employ MORBO in conjunction with the improved HOGP model to perform composite BO over high-dimensional outcome spaces (images).…”

Section: Composite Multi-objective Optimization Over High-dimensional...mentioning

confidence: 99%

“…We compare our multi-objective optimization approach (HOGP+MORBO) with current MORBO (GP+MORBO) (Daulton et al, 2021) on the 177-dimensional optics optimization problem. The simulations generating the outputs of the elements are computed using a custom physics simulation engine.…”

Section: Multi-objective Design Of a Diffractive Optical Elementmentioning

confidence: 99%

“…Experimental Details We used the MORBO implementation as referenced in Daulton et al (2021). Each trial was initialized with 400 Sobol points and optimized the hypervolume improvement with batch sizes of 50 over 5000 function evaluations.…”

Section: C2 Diffractive Optical Element Designmentioning

confidence: 99%

“…In this work, we combine the model and sampling scheme from Maddox et al (2021a) with the recent MORBO algorithm for high-dimensional multi-objective Bayesian Optimization from Daulton et al (2021). We overcome additional memory scalability challenges by employing a mixed-precision compute paradigm and batching computations, enabling improved performance over existing baselines.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Optimizing High-Dimensional Physics Simulations via Composite Bayesian Optimization

Maddox¹,

Qi²,

Balandat³

2021

Preprint

View full text Add to dashboard Cite

Physical simulation-based optimization is a common task in science and engineering. Many such simulations produce image-or tensor-based outputs where the desired objective is a function of those outputs, and optimization is performed over a high-dimensional parameter space. We develop a Bayesian optimization method leveraging tensor-based Gaussian process surrogates and trust region Bayesian optimization to effectively model the image outputs and to efficiently optimize these types of simulations, including a radio-frequency tower configuration problem and an optical design problem.

show abstract

Section: Composite Multi-objective Optimization Over High-dimensional...mentioning

confidence: 99%

Section: Composite Multi-objective Optimization Over High-dimensional...mentioning

confidence: 99%

Section: Multi-objective Design Of a Diffractive Optical Elementmentioning

confidence: 99%

Section: C2 Diffractive Optical Element Designmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Optimizing High-Dimensional Physics Simulations via Composite Bayesian Optimization

Maddox¹,

Qi²,

Balandat³

2021

Preprint

View full text Add to dashboard Cite

show abstract

A multifidelity approach coupling parameter space reduction and nonintrusive POD with application to structural optimization of passenger ship hulls

Tezzele

Fabris

Sidari

et al. 2022

Numerical Meth Engineering

View full text Add to dashboard Cite

Nowadays, the shipbuilding industry is facing a radical change toward solutions with a smaller environmental impact. This can be achieved with low emissions engines, optimized shape designs with lower wave resistance and noise generation, and by reducing the metal raw materials used during the manufacturing. This work focuses on the last aspect by presenting a complete structural optimization pipeline for modern passenger ship hulls which exploits advanced model order reduction techniques to reduce the dimensionality of both input parameters and outputs of interest. We introduce a novel approach which incorporates parameter space reduction through active subspaces into the proper orthogonal decomposition with interpolation method. This is done in a multi‐fidelity setting. We test the whole framework on a simplified model of a midship section and on the full model of a passenger ship, controlled by 20 and 16 parameters, respectively. We present a comprehensive error analysis and show the capabilities and usefulness of the methods especially during the preliminary design phase, finding new unconsidered designs while handling high dimensional parameterizations.

show abstract

Proximal-exploration multi-objective Bayesian optimization for inverse identification of cyclic constitutive law of structural steels

Ohsaki

2022

Struct Multidisc Optim

View full text Add to dashboard Cite

Despite its importance in seismic response analysis, solving an inverse problem to identify the cyclic elastoplastic parameters for structural steels using conventional optimization algorithms still demands a substantial computational cost of repeatedly carrying out many nonlinear analyses. The parameters are commonly identified based on experimental measures from a single loading history, leading them to be biased and giving inaccurate predictions of structural behavior under other loading histories. To address these issues, we formulate a multi-objective inverse problem that simultaneously minimizes the error functions representing the differences between simulated responses and those measured experimentally from various cyclic tests of a steel specimen or a structural component. We then propose proximal-exploration multi-objective Bayesian optimization (MOBO) for solving the formulated inverse problem, resulting in an approximate Pareto front of parameters while limiting the number of costly simulations. MOBO sorts an initial Pareto front and constructs Gaussian process (GP) models for the error functions from a training dataset. It then relies on the hypervolume of the current solutions, the GP models, and a proximal exploration surrounding the current best compromise parameters to formulate an acquisition function that guides the improvement of the current so-

show abstract

Multi-Objective Bayesian Optimization over High-Dimensional Search Spaces

Cited by 7 publications

References 27 publications

Optimizing High-Dimensional Physics Simulations via Composite Bayesian Optimization

Optimizing High-Dimensional Physics Simulations via Composite Bayesian Optimization

A multifidelity approach coupling parameter space reduction and nonintrusive POD with application to structural optimization of passenger ship hulls

Proximal-exploration multi-objective Bayesian optimization for inverse identification of cyclic constitutive law of structural steels

Contact Info

Product

Resources

About