Adversarial Auto-Encoders

• Distribution of hidden code

• Give more details after GAN

Another Approach: q(z)->p(z)

• Explicitly enforce

Intuitively comprehend KL(p|q)

\(KL \in{[0,+\infty]}\)

• KL = 0 --> \(p\approx{q}\)

Minimize KL Divergence

• Evidence Lower BOund

\[ KL(q_\theta(z|x_i)||p(z)) \]

How to compute KL between q(z) and p(z)

我们所希望的两点：

• 重建变量
• 隐藏变量逼近p的分布