Presentation
HiMOSS: A Novel High-dimensional Multi-objective Optimization Method via Adaptive Gradient-Based Subspace Sampling for Analog Circuit Sizing
SessionAI for Analog Synthesis
DescriptionThis study presents a novel high-dimensional multi-objective optimization method via adaptive gradient-based subspace sampling for analog circuit sizing. To handle constrained multi-objective optimization, we exploit promising regions from a non-crowded Pareto front, with lightweight Bayesian optimization (BO) based on a novel approximate constrained expected hypervolume improvement. This lightweight BO is computational efficient with constant complexity concerning simulation numbers. To tackle high-dimensional challenges, we reduce the effective dimensionality around promising regions by sampling candidates in an adaptive subspace. The subspace is constructed with gradients and previous success steps with their significance decaying over iterations. The gradients are approximated by sparse regression without additional simulations. The experiments on synthetic benchmarks and analog circuits illustrate advantages of the proposed method over Bayesian and evolutionary baselines.
Event Type
Research Manuscript
TimeThursday, June 2710:30am - 10:45am PDT
Location3002, 3rd Floor
EDA
Analog CAD, Simulation, Verification and Test