Tiered Acquisition for Constrained Bayesian Optimization: An Application to Analog Circuits

TL;DR

This paper introduces a tiered Bayesian optimization method with multiple dominance among acquisition functions, effectively handling heavily constrained search spaces in analog circuit design, leading to fewer violations and better optimization within limited computational resources.

Contribution

It presents the first use of multiple dominance among acquisition functions in Bayesian optimization, specifically tailored for constrained analog circuit design.

Findings

Reduces constraint violations by up to 38%.

Improves target objective by up to 43%.

Validated on a 65 nm two-stage Miller operational amplifier.

Abstract

Analog circuit design can be considered as an optimization problem with the targeted circuit specifications as constraints. When stringent circuit specifications are considered, it is desired to have an optimization methodology that adapts well to heavily constrained search spaces. To this end, we propose a novel Bayesian optimization algorithm with a tiered ensemble of acquisition functions and demonstrate its considerable application potential for analog circuit design automation. Our method is the first to introduce the concept of multiple dominance among acquisition functions, allowing the search for the optimal solutions to be effectively bounded \emph{within} the predicted set of feasible solutions in a constrained search space. This has resulted in a significant reduction in constraint violations by the candidate solutions, leading to better-optimized designs within tight computational budgets. The methodology is validated in gain and area optimization of a two-stage Miller compensated operational amplifier in a 65 nm technology. In comparison to robust baselines and state-of-the-art algorithms, this method reduces constraint violations by up to 38% and improves the target objective by up to 43%. The source code of our algorithm is made available at https://github.com/riarashid/TRACE.