How to add regularizations in TensorFlow?

Lifu Huang picture Lifu Huang · May 9, 2016 · Viewed 71.3k times · Source

I found in many available neural network code implemented using TensorFlow that regularization terms are often implemented by manually adding an additional term to loss value.

My questions are:

  1. Is there a more elegant or recommended way of regularization than doing it manually?

  2. I also find that get_variable has an argument regularizer. How should it be used? According to my observation, if we pass a regularizer to it (such as tf.contrib.layers.l2_regularizer, a tensor representing regularized term will be computed and added to a graph collection named tf.GraphKeys.REGULARIZATOIN_LOSSES. Will that collection be automatically used by TensorFlow (e.g. used by optimizers when training)? Or is it expected that I should use that collection by myself?

Answer

Lukasz Kaiser picture Lukasz Kaiser · May 10, 2016

As you say in the second point, using the regularizer argument is the recommended way. You can use it in get_variable, or set it once in your variable_scope and have all your variables regularized.

The losses are collected in the graph, and you need to manually add them to your cost function like this.

  reg_losses = tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)
  reg_constant = 0.01  # Choose an appropriate one.
  loss = my_normal_loss + reg_constant * sum(reg_losses)

Hope that helps!