An Efficient Bayesian Optimization Approach for Automated Optimization of Analog Circuits

Lyu, Wenlong; Xue, Pan; Yang, Fan; Yan, Changhao; Hong, Zhiliang; Zeng, Xuan; Zhou, Dian

doi:10.1109/tcsi.2017.2768826

Cited by 189 publications

(99 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this section, we demonstrate the efficiency of our proposed optimization approach with two real-world analog circuits: power amplifier ( §5.1) and charge pump ( §5.2). We quantitatively compare our approach with three state-of-the-art algorithms: WEIBO [17], GASPAD [16] and DE [15]. The WEIBO method is a traditional single-fidelity GP-based BO approach with wEI function works as the acquisition function.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

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

Zhang

Lyu

Yang

et al. 2019

Proceedings of the 56th Annual Design Automation Conference 2019

Self Cite

View full text Add to dashboard Cite

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 blackbox functions separately. The nonlinear map between the lowfidelity model and high-fidelity model is also modelled as a Gaussian process. A fusing GP model which combines the low-and highfidelity 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.

show abstract

Section: Resultsmentioning

confidence: 99%

“…To chart a way forward out of the dilemma, the GP-based Bayesian optimization (BO) approach has been proposed recently to combine both the model-based and simulation-based approach [17]. Generally, Bayesian optimization approach consists of two key elements: the surrogate model and the acquisition function [26].…”

Section: Introductionmentioning

confidence: 99%

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

Zhang

Lyu

Yang

et al. 2019

Proceedings of the 56th Annual Design Automation Conference 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…The mean function m(x) can be any function, while the kernel function k(x i , x j ) has to make sure that the covariance matrix is a symmetric positive definite (SPD) matrix. In [2], constant mean function m(x) = µ 0 and the Gaussian kernel function…”

Section: Gaussian Process Regressionmentioning

confidence: 99%

“…Given a new input vector x, GPR model predicts the distribution of y ∼ N (µ(x), σ 2 (x)). The µ(x) and σ 2 (x) can be expressed as [2] µ (3), µ(x) can be viewed as the prediction, and σ 2 (x) can be viewed the confidence of the prediction. Denote θ as the vector of hyper parameters including the hyper parameters for the kernel function, and the additive noise.…”

Section: Gaussian Process Regressionmentioning

confidence: 99%

See 1 more Smart Citation

Bayesian Optimization Approach for Analog Circuit Synthesis Using Neural Network

Zhang

Lyu

Yang

et al. 2019

2019 Design, Automation &Amp; Test in Europe Conference &Amp; Exhibition (DATE)

Self Cite

View full text Add to dashboard Cite

Bayesian optimization with Gaussian process as surrogate model has been successfully applied to analog circuit synthesis. In the traditional Gaussian process regression model, the kernel functions are defined explicitly. The computational complexity of training is O(N 3 ), and the computation complexity of prediction is O(N 2 ), where N is the number of training data. Gaussian process model can also be derived from a weight space view, where the original data are mapped to feature space, and the kernel function is defined as the inner product of nonlinear features. In this paper, we propose a Bayesian optimization approach for analog circuit synthesis using neural network. We use deep neural network to extract good feature representations, and then define Gaussian process using the extracted features. Model averaging method is applied to improve the quality of uncertainty prediction. Compared to Gaussian process model with explicitly defined kernel functions, the neuralnetwork-based Gaussian process model can automatically learn a kernel function from data, which makes it possible to provide more accurate predictions and thus accelerate the follow-up optimization procedure. Also, the neural-network-based model has O(N ) training time and constant prediction time. The efficiency of the proposed method has been verified by two realworld analog circuits.

show abstract

CAD for Analog/Mixed‐Signal Integrated Circuits

Budak¹,

Pan²,

Chen³

et al. 2022

Advances in Semiconductor Technologies

View full text Add to dashboard Cite

An Efficient Bayesian Optimization Approach for Automated Optimization of Analog Circuits

Cited by 189 publications

References 31 publications

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

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

Bayesian Optimization Approach for Analog Circuit Synthesis Using Neural Network

CAD for Analog/Mixed‐Signal Integrated Circuits

Contact Info

Product

Resources

About