# Task Specific Adversarial Cost Function

arXiv: https://arxiv.org/abs/1609.08661 · HTML: https://mlsanity.com/paper/1609.08661/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Sep 2016.

## Built on by (most cited first, 1 of 1)

- [TWIST-GAN: Towards Wavelet Transform and Transferred GAN for Spatio-Temporal Single Image Super Resolution](https://mlsanity.com/paper/2104.10268/) (2021)

## Abstract (arXiv)

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.