Causal AI For AMS Circuit Design: Interpretable Parameter Effects Analysis
This work addresses the problem of interpretable and accurate AI for analog-mixed-signal circuit design, offering a more efficient and trustworthy automation tool for circuit designers, though it is incremental as it builds on existing causal methods applied to a specific domain.
The paper tackled the challenge of modeling analog-mixed-signal circuits with AI by proposing a causal-inference framework that discovers directed-acyclic graphs from simulation data and quantifies parameter impacts, achieving an average absolute error of less than 25% in reproducing simulation-based effects compared to over 80% for a neural network baseline.
Analog-mixed-signal (AMS) circuits are highly non-linear and operate on continuous real-world signals, making them far more difficult to model with data-driven AI than digital blocks. To close the gap between structured design data (device dimensions, bias voltages, etc.) and real-world performance, we propose a causal-inference framework that first discovers a directed-acyclic graph (DAG) from SPICE simulation data and then quantifies parameter impact through Average Treatment Effect (ATE) estimation. The approach yields human-interpretable rankings of design knobs and explicit 'what-if' predictions, enabling designers to understand trade-offs in sizing and topology. We evaluate the pipeline on three operational-amplifier families (OTA, telescopic, and folded-cascode) implemented in TSMC 65nm and benchmark it against a baseline neural-network (NN) regressor. Across all circuits the causal model reproduces simulation-based ATEs with an average absolute error of less than 25%, whereas the neural network deviates by more than 80% and frequently predicts the wrong sign. These results demonstrate that causal AI provides both higher accuracy and explainability, paving the way for more efficient, trustworthy AMS design automation.