Example-driven Parametrisations for Bayesian Shape Optimisation

Key points

• Hand-crafting one is a complex endeavour requiring domain expertise, and often yields implicit infeasible regions, artificial bounds, and coupled, unordered coordinates.1
• We instead learn the parameterisation from a collection of existing designs, applying principal component analysis to the deformations between shapes.1
• The result is a linear, interpretable search space in which the number of components explicitly trades expressivity against dimensionality.1
• Across aerofoils, wings, and radio-frequency cavities, spanning 2D geometry to 3D aerodynamics and electromagnetics, we show improved sample efficiency and the ability to explore beyond the confines of hand-crafted baselines.1

Sources (1)

• [1]Example-driven Parametrisations for Bayesian Shape Optimisation
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 01:57 PM

  Bayesian optimisation is the natural tool for shape design when objectives are expensive and non-differentiable, but it needs a compact yet expressive parameterisation of the search space.

  Hand-crafting one is a complex endeavour requiring domain expertise, and often yields implicit infeasible regions, artificial bounds, and coupled, unordered coordinates.

Extractive summary: sentences quoted from the sources.