Fast Surrogate-Assisted Constrained Multiobjective Optimization for Analog Circuit Sizing via Self-Adaptive Incremental Learning

Yin, Sen; Wang, Ruitao; Zhang, Jian; Liu, Xiaosen; Wang, Yan

doi:10.1109/tcad.2022.3221694

Cited by 13 publications

(3 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Local BO, sparse GPR model [85] GNN + WEI Amp (C-2, D-8), driver (C-1, D-6) Parasitic-aware, GNN w/ dropout [86] GPR + Acq ensemble Amp-1,2,3 (C-10, C-12, C-24), etc., Batch BO enabled by the ensemble [87] Add-GPR + UCB Amp, DC (C-na) LDE-aware, high-dimensional [89] GPR + WEI Op-Amp (C-na) Bi-level BO, compensation design [90] GPR + EI Amp-1,2 (C-10, C-12) Local penalization 1 [92] GPR + modified TS Amp-1,2 (C-11, C-43) Applied to technology migration [105] Online GPR Op-Amp-1,2 (C-11, C-21) Self-adaptive incremental learning [102] GPR + wPESC Amp-1,2 (C-10, C-11) Automatically choose test benches [103] GPR + EIM Op-Amp-1,2 (C-11, C-21) Asynchronous BO [104] Online GPR + EIM Op-Amp-1,2 (C-11, C-26), etc., Self-adaptive incremental learning [100] GPR + LCB/EI CP (C-36), Amp (C-12) Search in one-dimensional subspace [101] MT-GPR + EI Transformer (C-4), LNA (C-15), etc., Multitask NN as GPR kernel [229] GPR + WEI 5 OTAs, 2 VCOs, 2 SCFs (D-na), etc., Wire sizing, GPR guided by GNN [96] GPR + LCB Voltage regulator (C-17 + D-10), etc., Novel evolutionary algorithm [97] GPR + TS LNA (C/D-17) 2…”

Section: B Other Problems and Discussionmentioning

confidence: 99%

Automatic Design of a Broadband Directional Coupler via Bayesian Optimization

Gao

Zhang

Boning

2022

Conference on Lasers and Electro-Optics

View full text Add to dashboard Cite

show abstract

Section: B Other Problems and Discussionmentioning

confidence: 99%

Automatic Design of a Broadband Directional Coupler via Bayesian Optimization

Gao

Zhang

Boning

2022

Conference on Lasers and Electro-Optics

View full text Add to dashboard Cite

show abstract

“…Reference [13] utilizes the NSGA−II [14] to obtain the Pareto solution set and applied it to the design of ring oscillators. Reference [15] proposes an efficient surrogate−assisted constrained multi−objective evolutionary algorithm for analog circuit sizing, which has been shown to achieve better results compared to the NSGA−II. As research advances, the application of multi−objective optimization methods in circuit parameter optimization has become increasingly sophisticated, and the algorithms for obtaining the Pareto front are continually improving.…”

Section: Introductionmentioning

confidence: 99%

Deterministic Multi-Objective Optimization of Analog Circuits

Xu,

Zhao,

Liu

2024

Electronics

View full text Add to dashboard Cite

Stochastic optimization approaches benefit from random variance to produce a solution in a reasonable time frame that is good enough for solving the problem. Compared with them, deterministic optimization methods feature faster convergence rates and better reproducibility but may get stuck at a local optimum that is insufficient to solve the problem. In this paper, we propose a group-based deterministic optimization method, which can efficiently achieve comparable performance to heuristic optimization algorithms, such as particle swarm optimization. Moreover, the weighted sum method (WSM) is employed to further improve our deterministic optimization method to be multi-objective optimization, making it able to seek a balance among multiple conflicting circuit performance metrics. With a case study of three common analog circuits tested for our optimization methodology, the experimental results demonstrate that our proposed method can more efficiently reach a better estimation of the Pareto front compared to NSGA-II, a well-known multi-objective optimization approach.

show abstract

“…The automation in circuit design can be categorized into two types: Equation-based method and Simulation-based method [1], [8], [9]. In equation-based method, the analytical equations are used to model the circuit performances for a given set of design constraints.…”

Section: Introductionmentioning

confidence: 99%

Partition Bound Random Number-Based Particle Swarm Optimization for Analog Circuit Sizing

Shreeharsha,

Siddharth,

Vasantha

et al. 2023

IEEE Access

View full text Add to dashboard Cite

This work introduces a Partition Bound Particle Swarm Optimization (PB-PSO) algorithm to enhance convergence rates in analog circuit optimization. Two new parameters, ζ 1 and ζ 2 , are incorporated to adaptively update particle velocities based on iteration numbers. The parameter ζ 1 depends on the nonlinear convergence factor (α) and the number of iterations, N . The results indicate that ζ 1 's optimal value occurs with α = 4. ζ 2 partitions iterations into two regions, aiding local and global search. The PB-PSO algorithm, implemented in Python, demonstrates higher convergence rates than existing methods, with successful designs verified through Cadence-Virtuoso circuit simulations. The proposed PB-PSO algorithm converges in 15 and 13 iterations for differential amplifier and two-stage op-amp respectively. For a case study of two-stage amplifier, it achieves a gain of 60.4 dB with a phase margin of 79.76 • , meeting input specifications within constraints. The figure of merit was then evaluated using the obtained parameters, which turns out to be 0.275 V −2 . INDEX TERMS Particle swarm optimization (PSO), analog circuit sizing, low power, operational amplifiers, constrained optimization.

show abstract

Fast Surrogate-Assisted Constrained Multiobjective Optimization for Analog Circuit Sizing via Self-Adaptive Incremental Learning

Cited by 13 publications

References 51 publications

Automatic Design of a Broadband Directional Coupler via Bayesian Optimization

Automatic Design of a Broadband Directional Coupler via Bayesian Optimization

Deterministic Multi-Objective Optimization of Analog Circuits

Partition Bound Random Number-Based Particle Swarm Optimization for Analog Circuit Sizing

Contact Info

Product

Resources

About