A Fresh Look at Lamarckian Evolution and the Baldwin Effect

2026-05-27

AI Summary

This study systematically compares the performance of Lamarckian evolution, the Baldwin effect, and standard Darwinian evolution in combinatorial optimization, with a focus on the integration mechanisms between local search and evolutionary algorithms. Employing a unified experimental framework, the three strategies are evaluated on graph-based optimization benchmarks such as GraphBench, complemented by runtime-theoretic analysis of their asymptotic behavior. The work introduces, for the first time, a general and efficient parameter configuration that demonstrates the consistent superiority of Lamarckian and Baldwinian mechanisms over purely Darwinian evolution across most scenarios. These hybrid approaches achieve performance comparable to specialized heuristics and exact solvers, and outperform recent deep learning methods. Theoretical analysis further reveals their asymptotic runtime advantages.

Abstract

Baldwinian and Lamarckian evolution have existed for a long time in evolutionary algorithms (EAs) without ever dominating the academic literature or practical applications. In this work, we use modern empirical and theoretical methods to revisit Lamarckian and Baldwinian evolution and rigorously compare them with the generic Darwinian evolution. On the empirical side, we run a comprehensive suite of experiments on graphs from six different datasets from the recent GraphBench benchmark on Maximum Independent Set and Maximum Cut problems. Our results show that Baldwinian and Lamarckian evolution consistently outperform Darwinian evolution, confirming the great potential of local search augmented evolutionary algorithms. Notably, in the great majority of cases, all EAs outperform recent deep learning baselines and approach the performance of highly specialised heuristic and exact solvers. We furthermore report a high-performing set of generalist parameters for all studied evolution types that we hope will be of use to practitioners in future. On the theoretical side, we extend the existing Deceptive Leading Block benchmark to arbitrary block length and use tools from modern theoretical runtime analysis to prove upper and lower bounds on the expected runtime. For block lengths greater than two, Baldwinian evolution is asymptotically faster than Lamarckian which is asymptotically faster than Darwinian evolution. When accounting for the cost of the local search procedure in fitness evaluations, the ordering depends on the implementation with Baldwinian evolution staying fastest from small block lengths onwards, explaining its strong empirical performance.

Problem

• Lamarckian evolution
• Baldwin Effect
• evolutionary algorithms
• combinatorial optimization
• runtime analysis

Innovation

• Lamarckian evolution
• Baldwin effect
• evolutionary algorithms
• local search
• runtime analysis