Basics of Graphs / Flow Control

[mig]

Hello,
I have a couple of questions regarding flow control in tensor flow/ Edward.

1. I define the following random variables:

   z = Poisson(tf.ones(1))
   x = Gamma(concentration=tf.ones(1), rate=z)
   y = Normal(loc=x + tf.ones(1), scale=0.005 * tf.ones(1))

After starting a session, I sample from them.

sess = ed.get_session()
[z.sample().eval(), x.sample().eval(), y.sample().eval()]

a) Every time I sample a variable the entire graph is traverse until that node and the value is returned but the intermediate values are not stored. Is this correct?
b) is there a way of sampling the entire graph once and report the value of every node at that particular sample?

2. Now, I redefine the model introducing flow control. Depending on the value of a previous variable, I sample from a Gamma distribution or from a Gaussian:

   z = Poisson(tf.ones(1))
   zp = tf.multiply(tf.constant(1, dtype=tf.float32), z)
   with tf.control_dependencies([zp]):
        comparison = tf.equal(zp, tf.zeros(1))
        with tf.control_dependencies([comparison]):
            def if_false():
                   y = Gamma(concentration=tf.ones(1), rate=zp)
                   return y
            def if_true():
                   x = Normal(loc=zp, scale=0.005 * tf.ones(1))
                   return x
        new_rv = tf.where(comparison, if_true(), if_false())
   

a) Is this the most compact way of writing this code?
b) in this case, I can sample from z and new_rv but not from the intermediate variables. Again, is there any way of accessing all the node values from a sample?

Thanks !

[dustin]

@mig

a) Every time I sample a variable the entire graph is traverse until that node and the value is returned but the intermediate values are not stored. Is this correct?
b) is there a way of sampling the entire graph once and report the value of every node at that particular sample?

Intermediate values are not stored unless you query them in the same session run. You can do so, for example, with

sess.run([z, x, y])

@mig

a) Is this the most compact way of writing this code?

I don’t think you need the tf.control_dependencies. The following works:

z = Poisson(tf.ones(1))
zp = 1.0 * z
comparison = tf.equal(zp, tf.zeros(1))
def if_false():
  y = Gamma(concentration=tf.ones(1), rate=zp)
  return y
def if_true():
  x = Normal(loc=zp, scale=0.005 * tf.ones(1))
  return x
new_rv = tf.where(comparison, if_true, if_false)

@mig

b) in this case, I can sample from z and new_rv but not from the intermediate variables. Again, is there any way of accessing all the node values from a sample?

See previous answer for tensors you have access to. For values inside the body of a function, things are a bit more difficult. You’d have to get them to be outputted to a tensor in some way.