Efficient Multiple Starting Point Optimization for Automated Analog Circuit Optimization via Recycling Simulation Data

Lyu

Proceedings of the 56th Annual Design Automation Conference 2019

et al. 2019

Self 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.

Section: Bayesian Optimization Based On the Multi-fidelity Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

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

Lyu

Proceedings of the 56th Annual Design Automation Conference 2019

et al. 2019

Self Cite

“…Since the computational cost of circuit simulations can be prohibitively expensive, the required number of evaluations should be kept at a minimum level to accelerate the optimization process. Embodiments of simulation-based approaches include the simulated annealing (SA) [15], the evolutionary algorithm [16]- [18] [19], the multiple start points (MSP) algorithm [20] [21], and the particle swarm optimization (PSO) algorithm [22]- [24]. All of these proposed algorithms try to mimic the physical or biological process to fully explore the state space and avoid stuck in the local optimum.…”

Section: Introductionmentioning

confidence: 99%

An Efficient Batch-Constrained Bayesian Optimization Approach for Analog Circuit Synthesis via Multiobjective Acquisition Ensemble

IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst.

Yan

et al. 2022

Self Cite

Bayesian optimization is a promising methodology for analog circuit synthesis. However, the sequential nature of the Bayesian optimization framework significantly limits its ability to fully utilize real-world computational resources. In this paper, we propose an efficient parallelizable Bayesian optimization algorithm via Multi-objective ACquisition function Ensemble (MACE) to further accelerate the optimization procedure. By sampling query points from the Pareto front of the probability of improvement (PI), expected improvement (EI) and lower confidence bound (LCB), we combine the benefits of state-of-theart acquisition functions to achieve a delicate tradeoff between exploration and exploitation for the unconstrained optimization problem. Based on this batch design, we further adjust the algorithm for the constrained optimization problem. By dividing the optimization procedure into two stages and first focusing on finding an initial feasible point, we manage to gain more information about the valid region and can better avoid sampling around the infeasible area. After achieving the first feasible point, we favor the feasible region by adopting a specially designed penalization term to the acquisition function ensemble. The experimental results quantitatively demonstrate that our proposed algorithm can reduce the overall simulation time by up to 74× compared to differential evolution (DE) for the unconstrained optimization problem when the batch size is 15. For the constrained optimization problem, our proposed algorithm can speed up the optimization process by up to 15× compared to the weighted expected improvement based Bayesian optimization (WEIBO) approach, when the batch size is 15.

“…They employ optimization strategies to propose new candidates, and aim to better explore the design space to search for the global optimum. The corresponding optimization approaches include simulated annealing [5], particle swarm intelligence approach [6], evolutionary algorithm [7], and multi-start optimization algorithm [8]- [10]. Since the simulations are performed on-thefly, the number of simulations would even be lower than the model-based approaches.…”

Section: Introductionmentioning

confidence: 99%

“…By treating the circuit performance as a black-box function, the simulation-based approaches guide the search with a selection engine and invoke the circuit simulator on the fly. There are several popular simulation-based approaches, including simulated annealing (SA) [11], [12], multiple starting point (MSP) algorithm [6], [13], evolutionary algorithm [4], [14] and particle swarm optimization (PSO) algorithm [15], [16]. The limitation of the simulation-based approaches is their relatively low convergence rate.…”

Section: Introductionmentioning

confidence: 99%

Bayesian Optimization Approach for Analog Circuit Synthesis Using Neural Network

Lyu

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

et al. 2019

Self 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.