This paper is based on solving the problem of Conditional Risk Minimization. Mostly, the data we are working on in Machine Learning is an i.i.d data[independent and identically distributed data]. What is this data? Identical and Independent are terms used in Probability. A common example of an identical and independent data can be a throw of a coin:
Independent: All throws of coin are independent. No memory is stored about the previous throw.
Identical: The resulting distribution is identical which means that we know about the final result: [P(Head) = 1/2, P(Tail) = 1/2].
Coming back to the point from this brief digression, Conditional risk minimization is trying to solve the problem when the data is stochastic. Given a loss function and a set of hypotheses, i...
In the last few years, deep neural networks have lead to breakthrough results on a variety of pattern recognition problems, such as computer vision and voice recognition. One of the essential components leading to these results has been a special kind of neural network called a convolutional neural network.
The paper proposes an adversarial approach for estimating generative models where one model (generative model) tries to learn a data distribution and another model (discriminative model) tries to distinguish between samples from the generative model and original data distribution.