Continuous Program Search

TL;DR

This paper introduces a continuous program space for genetic programming, enabling semantically meaningful mutations that improve search efficiency and strategy discovery in financial trading tasks.

Contribution

It proposes a novel method to learn a latent space with behavioral meaning and designs mutation operators exploiting this structure, enhancing evolutionary search performance.

Findings

Geometry-compiled mutation outperforms isotropic Gaussian mutation in efficiency.

Learned mutation operators discover strong trading strategies with fewer evaluations.

Faster convergence and more reliable progress in strategy optimization.

Abstract

Genetic Programming yields interpretable programs, but small syntactic mutations can induce large, unpredictable behavioral shifts, degrading locality and sample efficiency. We frame this as an operator-design problem: learn a continuous program space where latent distance has behavioral meaning, then design mutation operators that exploit this structure without changing the evolutionary optimizer. We make locality measurable by tracking action-level divergence under controlled latent perturbations, identifying an empirical trust region for behavior-local continuous variation. Using a compact trading-strategy DSL with four semantic components (long/short entry and exit), we learn a matching block-factorized embedding and compare isotropic Gaussian mutation over the full latent space to geometry-compiled mutation that restricts updates to semantically paired entry--exit subspaces and proposes directions using a learned flow-based model trained on logged mutation outcomes. Under identical $(\mu+\lambda)$ evolution strategies and fixed evaluation budgets across five assets, the learned mutation operator discovers strong strategies using an order of magnitude fewer evaluations and achieves the highest median out-of-sample Sharpe ratio. Although isotropic mutation occasionally attains higher peak performance, geometry-compiled mutation yields faster, more reliable progress, demonstrating that semantically aligned mutation can substantially improve search efficiency without modifying the underlying evolutionary algorithm.