# Exploiting Function-Family Structure in Analog Circuit Optimization

arXiv: https://arxiv.org/abs/2512.00712 · HTML: https://mlsanity.com/paper/2512.00712/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 30 references that are in the map.
- First posted on arXiv 30 Nov 2025.

## Builds on (most cited first, 7 of 7)

- [The CMA Evolution Strategy: A Tutorial](https://mlsanity.com/paper/1604.00772/) (2016)
- [SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization](https://mlsanity.com/paper/2109.09831/) (2021)
- [Uncertainty-Aware Search Framework for Multi-Objective Bayesian Optimization](https://mlsanity.com/paper/2204.05944/) (2022)
- [Versatile Black-Box Optimization](https://mlsanity.com/paper/2004.14014/) (2020)
- [Black-Box Optimization Revisited: Improving Algorithm Selection Wizards through Massive Benchmarking](https://mlsanity.com/paper/2010.04542/) (2020)
- [An Efficient Batch Constrained Bayesian Optimization Approach for Analog Circuit Synthesis via Multi-objective Acquisition Ensemble](https://mlsanity.com/paper/2106.15412/) (2021)
- [Escaping local minima with derivative-free methods: a numerical investigation](https://mlsanity.com/paper/1812.11343/) (2018)

## Built on by (most cited first, 2 of 2)

- [TabPFN-3: Technical Report](https://mlsanity.com/paper/2605.13986/) (2026)
- [Benchmarking Tabular Foundation Models as Surrogates in Expensive Evolutionary Optimization](https://mlsanity.com/paper/2609.18130/) (2026)

## Abstract (arXiv)

Analog circuit optimization is typically framed as black-box search over arbitrary smooth functions, yet device physics constrains performance mappings to structured families: exponential device laws, rational transfer functions, and regime-dependent dynamics. Off-the-shelf Gaussian-process surrogates impose globally smooth, stationary priors that are misaligned with these regime-switching primitives and can severely misfit highly nonlinear circuits at realistic sample sizes (50--100 evaluations). We demonstrate that pre-trained tabular models encoding these primitives enable reliable optimization without per-circuit engineering. Circuit Prior Network (CPN) combines a tabular foundation model (TabPFN v2) with Direct Expected Improvement (DEI), computing expected improvement exactly under discrete posteriors rather than Gaussian approximations. Across 6 circuits and 25 baselines, structure-matched priors achieve R2 ≈ 0.99 in small-sample regimes where GP-Mat'ern attains only R2 = 0.16 on Bandgap, deliver 1.05--3.81× higher FoM with 3.34--11.89× fewer iterations, and suggest a shift from hand-crafting models as priors toward systematic physics-informed structure identification. Our code will be made publicly available upon paper acceptance.