Integer Natural Evolution Strategies

2026-08-24

AI Summary

本文针对整数优化问题，提出了一种基于$\ell_1$-范数和双几何分布的整数自然进化策略（INES），通过自然梯度信号调整步长，展示了其在高维椭球问题上的优势。

Abstract

While contemporary Evolution Strategies handle integer optimization problems effectively, their adaptation mechanism is grounded in $\ell_2$-based Gaussian models, which are not native to the integer lattice. In contrast, the $\ell_1$-norm provides the natural measure of displacement on $\mathbb{Z}^n$, with the double geometric distribution as its canonical mutation operator. In this work, we derive a fully $\ell_1$-native step-size adaptation mechanism from first principles and propose an Integer Natural Evolution Strategy. We show that the DG distribution belongs to the exponential family, and that its sufficient statistic $|z|$ yields a natural-gradient signal for dispersion adaptation. By accumulating this signal via an evolution path, we obtain a fading-memory online estimator of the natural gradient, following Ollivier (2018). This establishes that DG-based step-size adaptation arises directly from the statistical structure of the mutation distribution, rather than as a discrete analog of continuous ES mechanisms. Empirical results on integer quadratic benchmarks show that \textsc{INES} learns meaningful coordinate-wise step-sizes and is competitive with integer-handling CMA-ES baselines. Its advantages are most visible in high-dimensional Ellipsoidal problems and in robust convergence at larger dimensions.

Problem

• Integer Optimization
• Evolution Strategies
• Natural Gradient
• $\ell_1$-norm
• Double Geometric Distribution

Innovation

• Integer Natural Evolution Strategy
• ell_1-norm
• Double Geometric Distribution
• Natural Gradient
• Step-size Adaptation