Causal-Guided Dimension Reduction for Efficient Pareto Optimization

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Jayasuriya, Dinithi, Kumar, Divake, Senthilkumar, Sureshkumar, Naik, Devashri, Darabi, Nastaran, Trivedi, Amit Ranjan
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909837255770112
author Jayasuriya, Dinithi
Kumar, Divake
Senthilkumar, Sureshkumar
Naik, Devashri
Darabi, Nastaran
Trivedi, Amit Ranjan
author_facet Jayasuriya, Dinithi
Kumar, Divake
Senthilkumar, Sureshkumar
Naik, Devashri
Darabi, Nastaran
Trivedi, Amit Ranjan
contents Multi-objective optimization of analog circuits is hindered by high-dimensional parameter spaces, strong feedback couplings, and expensive transistor-level simulations. Evolutionary algorithms such as Non-dominated Sorting Genetic Algorithm II (NSGA-II) are widely used but treat all parameters equally, thereby wasting effort on variables with little impact on performance, which limits their scalability. We introduce CaDRO, a causal-guided dimensionality reduction framework that embeds causal discovery into the optimization pipeline. CaDRO builds a quantitative causal map through a hybrid observational-interventional process, ranking parameters by their causal effect on the objectives. Low-impact parameters are fixed to values from high-quality solutions, while critical drivers remain active in the search. The reduced design space enables focused evolutionary optimization without modifying the underlying algorithm. Across amplifiers, regulators, and RF circuits, CaDRO converges up to 10$\times$ faster than NSGA-II while preserving or improving Pareto quality. For instance, on the Folded-Cascode Amplifier, hypervolume improves from 0.56 to 0.94, and on the LDO regulator from 0.65 to 0.81, with large gains in non-dominated solutions.
format Preprint
id arxiv_https___arxiv_org_abs_2510_09941
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Causal-Guided Dimension Reduction for Efficient Pareto Optimization
Jayasuriya, Dinithi
Kumar, Divake
Senthilkumar, Sureshkumar
Naik, Devashri
Darabi, Nastaran
Trivedi, Amit Ranjan
Neural and Evolutionary Computing
Systems and Control
Multi-objective optimization of analog circuits is hindered by high-dimensional parameter spaces, strong feedback couplings, and expensive transistor-level simulations. Evolutionary algorithms such as Non-dominated Sorting Genetic Algorithm II (NSGA-II) are widely used but treat all parameters equally, thereby wasting effort on variables with little impact on performance, which limits their scalability. We introduce CaDRO, a causal-guided dimensionality reduction framework that embeds causal discovery into the optimization pipeline. CaDRO builds a quantitative causal map through a hybrid observational-interventional process, ranking parameters by their causal effect on the objectives. Low-impact parameters are fixed to values from high-quality solutions, while critical drivers remain active in the search. The reduced design space enables focused evolutionary optimization without modifying the underlying algorithm. Across amplifiers, regulators, and RF circuits, CaDRO converges up to 10$\times$ faster than NSGA-II while preserving or improving Pareto quality. For instance, on the Folded-Cascode Amplifier, hypervolume improves from 0.56 to 0.94, and on the LDO regulator from 0.65 to 0.81, with large gains in non-dominated solutions.
title Causal-Guided Dimension Reduction for Efficient Pareto Optimization
topic Neural and Evolutionary Computing
Systems and Control
url https://arxiv.org/abs/2510.09941