paper-with-me

홈 › Papers

Why can genetic algorithms work in high-dimensional search spaces?

2026-06-29 · Stephen Whitelam arxiv

We show that the effective dynamics of the elitist $(1+M)$ genetic algorithm is, in the limit of small mutations, clipped gradient descent on the loss in the presence of anisotropic Gaussian white noise. In expectation, therefore, a simple mutation-selection genetic algorithm follows the gradient of the loss, without explicit calculation of gradients and without averaging over loss evaluations. The genetic algorithm is slower than gradient descent because of the noise that acts in directions transverse to the gradient. However, this slowdown is controlled not by the number of parameters of the search space but by the effective rank of the Hessian of the loss function. For the concentrated Hessian spectra observed in neural-network loss functions the effective rank can be far smaller than the number of parameters, which may explain why genetic algorithms can scale to large search spaces.

📄 PDF Abstract BibTeX arXiv:2606.30619

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

HYB-PARSIMONY: A hybrid approach combining Particle Swarm Optimization and Genetic Algorithms to find parsimonious models in high-dimensional datasets

2023-12-01 · Neurocomputing 2023 12 · J. Divasón, A. Pernia-Espinoza, F.J. Martinez-de-Pison

The PSO-PARSIMONY methodology (a heuristic for finding accurate and low-complexity models with particle swarm optimization (PSO)) allows obtaining machine learning models with a good balance between accuracy and complexi…

ELENA: Epigenetic Learning through Evolved Neural Adaptation

2025-01-10 · Boris Kriuk, Keti Sulamanidze, Fedor Kriuk

Despite the success of metaheuristic algorithms in solving complex network optimization problems, they often struggle with adaptation, especially in dynamic or high-dimensional search spaces. Traditional approaches can b…

Traveling Salesman Problem

Genetically Modified Wolf Optimization with Stochastic Gradient Descent for Optimising Deep Neural Networks

2023-01-21 · Manuel Bradicic, Michal Sitarz, Felix Sylvest Olesen

When training Convolutional Neural Networks (CNNs) there is a large emphasis on creating efficient optimization algorithms and highly accurate networks. The state-of-the-art method of optimizing the networks is done by u…

An Evolutional Neural Network Framework for Classification of Microarray Data

2024-11-20 · Maryam Eshraghi Evari, Md Nasir Sulaiman, Amir Rajabi Behjat

DNA microarray gene-expression data has been widely used to identify cancerous gene signatures. Microarray can increase the accuracy of cancer diagnosis and prognosis. However, analyzing the large amount of gene expressi…

feature selectionPrognosis

Can Genetic Programming Do Manifold Learning Too?

2019-02-08 · Andrew Lensen, Bing Xue, Mengjie Zhang

Exploratory data analysis is a fundamental aspect of knowledge discovery that aims to find the main characteristics of a dataset. Dimensionality reduction, such as manifold learning, is often used to reduce the number of…

Dimensionality Reduction