标题： 多种群GAN训练：分析共进化算法 显示英文标题

标题： Multi-population GAN Training: Analyzing Co-Evolutionary Algorithms

摘要： 生成对抗网络（GANs）是强大的生成模型，但由于模式崩溃和不稳定性等病理问题，在训练上仍然具有挑战性。 最近的研究探索了共同进化方法，其中生成器和判别器的种群被共同进化，作为一种有前景的解决方案。 本文对不同的共同进化GAN训练策略进行了实证分析，重点研究了选择和替换机制的影响。 我们在合成低维数据集（blob和高斯混合）以及基于图像的基准（MNIST）上，比较了（mu,lambda）、带有精英策略的（mu+lambda）以及带有锦标赛选择的（mu+lambda）共同进化方案，同时还包括一个非共同进化的人口基础的多生成器多判别器GAN基线。 结果表明，完整的世代替换，即（mu,lambda），在样本质量和多样性方面始终表现更好，尤其是在结合较大的后代规模时。 相比之下，精英策略容易过早收敛并导致多样性减少。 这些发现强调了在共同进化GAN训练中平衡探索与利用动态的重要性，并为设计更有效的基于种群的生成模型提供了指导。 显示英文摘要

摘要： Generative adversarial networks (GANs) are powerful generative models but remain challenging to train due to pathologies suchas mode collapse and instability. Recent research has explored co-evolutionary approaches, in which populations of generators and discriminators are evolved, as a promising solution. This paper presents an empirical analysis of different coevolutionary GAN training strategies, focusing on the impact of selection and replacement mechanisms. We compare (mu,lambda), (mu+lambda) with elitism, and (mu+lambda) with tournament selection coevolutionary schemes, along with a non-evolutionary population based multi-generator multi-discriminator GAN baseline, across both synthetic low-dimensional datasets (blob and gaussian mixtures) and an image-based benchmark (MNIST). Results show that full generational replacement, i.e., (mu,lambda), consistently outperforms in terms of both sample quality and diversity, particularly when combined with larger offspring sizes. In contrast, elitist approaches tend to converge prematurely and suffer from reduced diversity. These findings highlight the importance of balancing exploration and exploitation dynamics in coevolutionary GAN training and provide guidance for designing more effective population-based generative models.