Alternating Back-Propagation for Generator Network
Tian Han †, Yang Lu †, Song-Chun Zhu, Ying Nian Wu Department of Statistics, University of California, Los Angeles, USA
Abstract
This paper proposes an alternating back-propagation algorithm for learning the generator network model. The model is a non-linear generalization of factor analysis. In this model, the mapping from the continuous latent factors to the observed signal is parametrized by a convolutional neural network. The alternating back-propagation algorithm iterates the following two steps: (1) Inferential back-propagation, which infers the latent factors by Langevin dynamics or gradient descent. (2) Learning back-propagation, which updates the parameters given the inferred latent factors by gradient descent. The gradient computations in both steps are powered by back-propagation, and they share most of their code in common. We show that the alternating back-propagation algorithm can learn realistic generator models of natural images, video sequences, and sounds. Moreover, it can also be used to learn from incomplete or indirect training data.
中文速览
生成器网络（generator network）能把低维隐变量映射成逼真的图像、视频或声音，但训练它的难点在于：隐变量是未知的，必须边推断隐变量边学习网络参数。现有方法（如VAE、GAN）都需要额外引入一个辅助网络来绕开这一推断问题，结构较为复杂。本文提出"交替反向传播"（alternating back-propagation）算法，交替执行两步：先用朗之万动力学或梯度下降对每个训练样本推断其隐变量（推断反向传播），再固定隐变量用梯度下降更新网络权重（学习反向传播），两步均由同一套反向传播代码驱动，无需任何额外网络。实验表明，该算法不仅能在自然图像、视频、声音上学到高质量生成模型，还能从残缺或间接观测数据中有效学习，这正是生成模型相比判别模型的独特优势所在。
原文 arXiv:1606.08571;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1606.08571v4