Task Specific Adversarial Cost Function

Antonia Creswell, Anil A. Bharath
(Submitted on 27 Sep 2016)

Abstract:

The cost function used to train a generative model should fit the
purpose of the model. If the model is intended for tasks such as
generating perceptually correct samples, it is beneficial to maximise
the likelihood of a sample drawn from the model, Q, coming from the
same distribution as the training data, P. This is equivalent to
minimising the Kullback-Leibler (KL) distance, KL[Q||P]. However, if
the model is intended for tasks such as retrieval or classification it
is beneficial to maximise the likelihood that a sample drawn from the
training data is captured by the model, equivalent to minimising
KL[P||Q]. The cost function used in adversarial training optimises the
Jensen-Shannon entropy which can be seen as an even interpolation
between KL[Q||P] and KL[P||Q]. Here, we propose an alternative
adversarial cost function which allows easy tuning of the model for
either task. Our task specific cost function is evaluated on a dataset
of hand-written characters in the following tasks: Generation,
retrieval and one-shot learning.

Resource Type: