Transfer Learning in Bayesian Optimization for Aircraft Design

arXiv stat.ML / 4/1/2026

💬 OpinionSignals & Early TrendsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper proposes a transfer-learning approach for Bayesian optimization that mitigates the cold-start problem by leveraging source data to accelerate optimization for a target task.
It integrates an ensemble of transfer-learned surrogate models into a constrained Bayesian optimization framework tailored to aircraft design optimization.
To handle heterogeneous aircraft design spaces, the method uses partial least squares (PLS) for dimension reduction and a meta-data-based surrogate selection strategy for heterogeneous constraints.
Experiments on numerical benchmarks and an aircraft conceptual design optimization case show faster convergence in early iterations and improved prediction accuracy for both objectives and constraints versus standard Bayesian optimization.

Abstract

The use of transfer learning within Bayesian optimization addresses the disadvantages of the so-called \textit{cold start} problem by using source data to aid in the optimization of a target problem. We present a method that leverages an ensemble of surrogate models using transfer learning and integrates it in a constrained Bayesian optimization framework. We identify challenges particular to aircraft design optimization related to heterogeneous design variables and constraints. We propose the use of a partial-least-squares dimension reduction algorithm to address design space heterogeneity, and a \textit{meta} data surrogate selection method to address constraint heterogeneity. Numerical benchmark problems and an aircraft conceptual design optimization problem are used to demonstrate the proposed methods. Results show significant improvement in convergence in early optimization iterations compared to standard Bayesian optimization, with improved prediction accuracy for both objective and constraint surrogate models.