An Efficient Multi-fidelity Bayesian Optimization Approach for Analog Circuit Synthesis

TL;DR

This paper introduces a multi-fidelity Bayesian optimization method for analog circuit synthesis that significantly reduces computational costs by effectively combining low- and high-fidelity models using Gaussian Processes.

Contribution

It proposes a novel fusing Gaussian Process model that integrates low- and high-fidelity data for more efficient circuit optimization.

Findings

Reduces simulation time by up to 65.5% compared to single-fidelity methods.

Achieves more stable and practical optimization performance.

Effectively balances exploration and exploitation through a new acquisition function.

Abstract

This paper presents an efficient multi-fidelity Bayesian optimization approach for analog circuit synthesis. The proposed method can significantly reduce the overall computational cost by fusing the simple but potentially inaccurate low-fidelity model and a few accurate but expensive high-fidelity data. Gaussian Process (GP) models are employed to model the low- and high-fidelity black-box functions separately. The nonlinear map between the low-fidelity model and high-fidelity model is also modelled as a Gaussian process. A fusing GP model which combines the low- and high-fidelity models can thus be built. An acquisition function based on the fusing GP model is used to balance the exploitation and exploration. The fusing GP model is evolved gradually as new data points are selected sequentially by maximizing the acquisition function. Experimental results show that our proposed method reduces up to 65.5\% of the simulation time compared with the state-of-the-art single-fidelity Bayesian optimization method, while exhibiting more stable performance and a more promising practical prospect.