论文标题
深层生成模型和生成AI的多样性
Diversity in deep generative models and generative AI
论文作者
论文摘要
基于解码器的机器学习生成算法，例如生成对抗网络（GAN），变异自动编码器（VAE），变压器在构造与训练集合中类似的对象时会显示出令人印象深刻的结果。但是，新对象的产生主要基于对训练数据集的隐藏结构的理解，然后是从多维正常变量中进行采样。特别是每个样本与其他样本独立，可以反复提出相同类型的对象。为了解决这一缺点，我们引入了一种基于内核的度量量化方法，该方法可以通过将其整体近似，甚至远离已经从该分布中得出的元素来从给定的目标度量中产生新对象。这样可以确保生产对象的更好多样性。该方法在经典的机器学习基准测试中进行了测试。
The decoder-based machine learning generative algorithms such as Generative Adversarial Networks (GAN), Variational Auto-Encoders (VAE), Transformers show impressive results when constructing objects similar to those in a training ensemble. However, the generation of new objects builds mainly on the understanding of the hidden structure of the training dataset followed by a sampling from a multi-dimensional normal variable. In particular each sample is independent from the others and can repeatedly propose same type of objects. To cure this drawback we introduce a kernel-based measure quantization method that can produce new objects from a given target measure by approximating it as a whole and even staying away from elements already drawn from that distribution. This ensures a better diversity of the produced objects. The method is tested on classic machine learning benchmarks.
