@article{goodfellow_generative_2014,
title = {Generative {Adversarial} {Networks}},
url = {http://arxiv.org/abs/1406.2661},
abstract = {We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. The training procedure for G is to maximize the probability of D making a mistake. This framework corresponds to a minimax two-player game. In the space of arbitrary functions G and D, a unique solution exists, with G recovering the training data distribution and D equal to 1/2 everywhere. In the case where G and D are defined by multilayer perceptrons, the entire system can be trained with backpropagation. There is no need for any Markov chains or unrolled approximate inference networks during either training or generation of samples. Experiments demonstrate the potential of the framework through qualitative and quantitative evaluation of the generated samples.},
urldate = {2019-11-28},
journal = {arXiv:1406.2661 [cs, stat]},
author = {Goodfellow, Ian J. and Pouget-Abadie, Jean and Mirza, Mehdi and Xu, Bing and Warde-Farley, David and Ozair, Sherjil and Courville, Aaron and Bengio, Yoshua},
month = jun,
year = {2014},
note = {ZSCC: 0000010
arXiv: 1406.2661},
keywords = {Adversarial attacks, Classical ML, Implementation, Machine learning}
}
@article{tran_deep_2017,
title = {Deep {Probabilistic} {Programming}},
url = {http://arxiv.org/abs/1701.03757},
abstract = {We propose Edward, a Turing-complete probabilistic programming language. Edward defines two compositional representations---random variables and inference. By treating inference as a first class citizen, on a par with modeling, we show that probabilistic programming can be as flexible and computationally efficient as traditional deep learning. For flexibility, Edward makes it easy to fit the same model using a variety of composable inference methods, ranging from point estimation to variational inference to MCMC. In addition, Edward can reuse the modeling representation as part of inference, facilitating the design of rich variational models and generative adversarial networks. For efficiency, Edward is integrated into TensorFlow, providing significant speedups over existing probabilistic systems. For example, we show on a benchmark logistic regression task that Edward is at least 35x faster than Stan and 6x faster than PyMC3. Further, Edward incurs no runtime overhead: it is as fast as handwritten TensorFlow.},
urldate = {2019-11-27},
journal = {arXiv:1701.03757 [cs, stat]},
author = {Tran, Dustin and Hoffman, Matthew D. and Saurous, Rif A. and Brevdo, Eugene and Murphy, Kevin and Blei, David M.},
month = mar,
year = {2017},
note = {ZSCC: 0000108
arXiv: 1701.03757},
keywords = {Bayesian inference, Implementation, Machine learning, Probabilistic programming}
}