We present Turbo-Sim, a generalised autoencoder framework derived from principles of information theory that can be used as a generative model. By maximising the mutual information between the input and the output of both the encoder and the decoder, we are able to rediscover the loss terms usually found in adversarial autoencoders and generative adversarial networks, as well as various more sophisticated related models. Our generalised framework makes these models mathematically interpretable and allows for a diversity of new ones by setting the weight of each loss term separately. The framework is also independent of the intrinsic architecture of the encoder and the decoder thus leaving a wide choice for the building blocks of the whole network. We apply Turbo-Sim to a collider physics generation problem: the transformation of the properties of several particles from a theory space, right after the collision, to an observation space, right after the detection in an experiment.
翻译:我们展示了Turbo-Sim, 这是一种源于信息理论原则的通用自动编码框架,可以用作基因模型。通过最大限度地扩大编码器和解码器输入和输出之间的相互信息,我们能够重新发现在对抗性自动编码器和基因对抗网络中通常发现的损失条件,以及各种更复杂的相关模型。我们的一般框架使这些模型可以进行数学解释,并允许通过分别设定每个损失术语的重量而使新的模型多样化。这个框架还独立于编码器和解码器的内在结构,从而为整个网络的构件留下一个广泛的选择。我们把图博-Sim应用到一个对流物理生成问题:将数颗粒的特性从一个理论空间,即碰撞后,转换到一个观测空间,就在实验中探测到之后。