Adversarial Auto-Encoders

目录

• Another Approach: q(z)->p(z)
  • Intuitively comprehend KL(p|q)
• Minimize KL Divergence
  • How to compute KL between q(z) and p(z)

• Distribution of hidden code

• Give more details after GAN

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

• Explicitly enforce

Intuitively comprehend KL(p|q)

KL∈[0,+∞]$KL\in [0,+\mathrm{\infty }]$

• KL = 0 --> p≈q$p\approx q$

Minimize KL Divergence

• Evidence Lower BOund

KL(qθ(z|xi)||p(z))$$KL(q_{\theta }(z|x_i)||p(z))$$

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