COSMO: a correlation sensitive mutation operator for multi-objective optimization

Authors:
Varun Aggarwal;Una-May O'Reilly
Affiliations:
Massachuestts Institute of Technology, Cambridge, MA;Massachuestts Institute of Technology, Cambridge, MA
Venue:
Proceedings of the 9th annual conference on Genetic and evolutionary computation
Year:
2007

Citing 10
Cited 0

An efficient DC root solving algorithm with guaranteed convergence for analog integrated CMOS circuits

Proceedings of the 1998 IEEE/ACM international conference on Computer-aided design
Multi-Objective Optimization Using Evolutionary Algorithms

Multi-Objective Optimization Using Evolutionary Algorithms
The Design of Innovation: Lessons from and for Competent Genetic Algorithms

The Design of Innovation: Lessons from and for Competent Genetic Algorithms
Reducing the time complexity of the derandomized evolution strategy with covariance matrix adaptation (CMA-ES)

Evolutionary Computation
NSGA-based parasitic-aware optimization of a 5GHz low-noise VCO

Proceedings of the 2004 Asia and South Pacific Design Automation Conference
Efficient Multiobjective Synthesis of Analog Circuits using Hierarchical Pareto-Optimal Performance Hypersurfaces

Proceedings of the conference on Design, Automation and Test in Europe - Volume 2
Approximating the Nondominated Front Using the Pareto Archived Evolution Strategy

Evolutionary Computation
Generation of yield-aware Pareto surfaces for hierarchical circuit design space exploration

Proceedings of the 43rd annual Design Automation Conference
Scalable Optimization via Probabilistic Modeling: From Algorithms to Applications (Studies in Computational Intelligence)

Scalable Optimization via Probabilistic Modeling: From Algorithms to Applications (Studies in Computational Intelligence)
Covariance Matrix Adaptation for Multi-objective Optimization

Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

This contribution is the first to discover exploitable structural features within circuit optimization problems (COP) and discuss how it is indicative of a general structure and possibly a 'measure of hardness' in real-world multi-objective optimization problems. We then present a methodology to exploit this structure in a multi-objective evolutionary algorithm by designing a novel Correlation Sensitive Mutation Operator, COSMO. COSMO is, at the least, universally applicable in the domain of circuits and we discuss how it can be easily extended to other domains. We discuss the rationale behind COSMO and interpret it in context of dimensional locality. We compare COSMO's performance with the traditional operators used for multi-objective optimization. For two instances of circuits, we show that COSMO gives significantly faster and better optimization than conventional operators. The paper also takes the first steps in thinking and interpreting how operators for MO-EAs should be designed.